http://wikis.swarthmore.edu/ling073/api.php?action=feedcontributions&feedformat=atom&user=Nfeldba1 2026-10-25T11:33:03Z User contributions MediaWiki 1.27.7 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5429 2017-05-11T17:21:19Z

<p>Nfeldba1: </p> <hr /> <div>==The Project==<br /> For my final project, I expanded my transducer until it reached 85% coverage, which involved adding words, disambiguations, and extra suffixes.<br /> <br /> My code can be found here: https://github.com/nfeldbaum/Khasi_Transducer<br /> <br /> ==The Results==<br /> <br /> I managed to reach 85.15% coverage on my initial 50,000 word corpus! However, I ended up adding a significant number of English words that were present to reach this amount. A truer measure of corpus coverage is the 80.50% coverage I get when I delete all the words that aren&#039;t part of Khasi.<br /> <br /> Instead of testing precision and recall against hand-annotated randomly selected forms, I decided to gather a further 25,000 words in order to test my transducer on a corpus it hadn&#039;t trained on. This new corpus can be found in the repository linked above under ling073-kha-corpus/kha.corpus.large.test.txt. On this test corpus, I achieved 83.39% coverage with English words included, and 80.50% coverage without English words - exactly the same as on my training corpus.<br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5428 2017-05-11T17:21:16Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala - unsure<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> ==Step 20: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.90%<br /> Top unknown words in the corpus:<br /> 12 kai<br /> 12 Friday<br /> 12 nongialam<br /> 12 jingshisha<br /> 12 jongki<br /> 12 shisien<br /> 12 men<br /> 12 tnat<br /> 12 Bangladesh<br /> 12 Mobile<br /> 12 Central<br /> 12 kadei<br /> 12 ngim<br /> 12 naba<br /> ==Step 21: added all the above words (and accompanying disambiguations) and reworked morphology with u, la, yn, ym, etc ==<br /> Coverage: 84.51%<br /> Top unknown words in the corpus:<br /> 12 kongsan<br /> 12 pyrda<br /> 12 tulop<br /> 12 Wahumkhrah<br /> 12 Municipal<br /> 12 pynbha<br /> 12 Bagan<br /> 12 thung<br /> 12 Executive<br /> 11 St<br /> 11 bat<br /> 11 pateng<br /> 11 shem<br /> 11 mon<br /> 11 shen<br /> ==Step 22: added all the above words (and accompanying disambiguations)==<br /> Coverage: 84.87%<br /> Top unknown words in the corpus:<br /> 11 pa<br /> 11 pyllait<br /> 11 dak<br /> 11 mariang<br /> 11 Inter<br /> 11 MDC<br /> 11 jam<br /> 11 NPP<br /> 11 khia<br /> 11 Education<br /> 11 kylleng<br /> 11 Adam<br /> 11 met<br /> 11 ïalade<br /> 11 RBYF<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5427 2017-05-11T17:20:50Z

<p>Nfeldba1: </p> <hr /> <div>==The Project==<br /> For my final project, I expanded my transducer until it reached 85% coverage, which involved adding words, disambiguations, and extra suffixes.<br /> <br /> My code can be found here: https://github.com/nfeldbaum/Khasi_Transducer<br /> <br /> ==The Results==<br /> <br /> I managed to reach 85.15% coverage on my initial 50,000 word corpus! However, I ended up adding a significant number of English words that were present to reach this amount. A truer measure of corpus coverage is the 80.50% coverage I get when I delete all the words that aren&#039;t part of Khasi.<br /> <br /> Instead of testing precision and recall against hand-annotated randomly selected forms, I decided to gather a further 25,000 words in order to test my transducer on a corpus it hadn&#039;t trained on. This new corpus can be found in the repository linked above under ling073-kha-corpus/kha.corpus.large.test.txt. On this test corpus, I achieved 83.39% coverage with English words included, and 80.50% coverage without English words - exactly the same as on my training corpus.</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5426 2017-05-11T16:37:28Z

<p>Nfeldba1: Blanked the page</p> <hr /> <div></div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5425 2017-05-11T16:37:23Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala - unsure<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> ==Step 20: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.90%<br /> Top unknown words in the corpus:<br /> 12 kai<br /> 12 Friday<br /> 12 nongialam<br /> 12 jingshisha<br /> 12 jongki<br /> 12 shisien<br /> 12 men<br /> 12 tnat<br /> 12 Bangladesh<br /> 12 Mobile<br /> 12 Central<br /> 12 kadei<br /> 12 ngim<br /> 12 naba<br /> ==Step 21: added all the above words (and accompanying disambiguations) and reworked morphology with u, la, yn, ym, etc ==<br /> Coverage: 84.51%<br /> Top unknown words in the corpus:<br /> 12 kongsan<br /> 12 pyrda<br /> 12 tulop<br /> 12 Wahumkhrah<br /> 12 Municipal<br /> 12 pynbha<br /> 12 Bagan<br /> 12 thung<br /> 12 Executive<br /> 11 St<br /> 11 bat<br /> 11 pateng<br /> 11 shem<br /> 11 mon<br /> 11 shen<br /> ==Step 22: added all the above words (and accompanying disambiguations)==<br /> Coverage: 84.87%<br /> Top unknown words in the corpus:<br /> 11 pa<br /> 11 pyllait<br /> 11 dak<br /> 11 mariang<br /> 11 Inter<br /> 11 MDC<br /> 11 jam<br /> 11 NPP<br /> 11 khia<br /> 11 Education<br /> 11 kylleng<br /> 11 Adam<br /> 11 met<br /> 11 ïalade<br /> 11 RBYF<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5424 2017-05-11T16:34:16Z

<p>Nfeldba1: /* Step 21: added all the above words (and accompanying disambiguations) and reworked morphology with u, la, yn, ym, etc */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala - unsure<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> ==Step 20: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.90%<br /> Top unknown words in the corpus:<br /> 12 kai<br /> 12 Friday<br /> 12 nongialam<br /> 12 jingshisha<br /> 12 jongki<br /> 12 shisien<br /> 12 men<br /> 12 tnat<br /> 12 Bangladesh<br /> 12 Mobile<br /> 12 Central<br /> 12 kadei<br /> 12 ngim<br /> 12 naba<br /> ==Step 21: added all the above words (and accompanying disambiguations) and reworked morphology with u, la, yn, ym, etc ==<br /> Coverage: 84.51%<br /> Top unknown words in the corpus:<br /> 12 kongsan<br /> 12 pyrda<br /> 12 tulop<br /> 12 Wahumkhrah<br /> 12 Municipal<br /> 12 pynbha<br /> 12 Bagan<br /> 12 thung<br /> 12 Executive<br /> 11 St<br /> 11 bat<br /> 11 pateng<br /> 11 shem<br /> 11 mon<br /> 11 shen<br /> ==Step 22: added all the above words (and accompanying disambiguations)==<br /> Coverage: 84.87%<br /> Top unknown words in the corpus:<br /> 11 pa<br /> 11 pyllait<br /> 11 dak<br /> 11 mariang<br /> 11 Inter<br /> 11 MDC<br /> 11 jam<br /> 11 NPP<br /> 11 khia<br /> 11 Education<br /> 11 kylleng<br /> 11 Adam<br /> 11 met<br /> 11 ïalade<br /> 11 RBYF<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5423 2017-05-11T16:00:57Z

<p>Nfeldba1: /* Step 20: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala - unsure<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> ==Step 20: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.90%<br /> Top unknown words in the corpus:<br /> 12 kai<br /> 12 Friday<br /> 12 nongialam<br /> 12 jingshisha<br /> 12 jongki<br /> 12 shisien<br /> 12 men<br /> 12 tnat<br /> 12 Bangladesh<br /> 12 Mobile<br /> 12 Central<br /> 12 kadei<br /> 12 ngim<br /> 12 naba<br /> ==Step 21: added all the above words (and accompanying disambiguations) and reworked morphology with u, la, yn, ym, etc ==<br /> Coverage: 84.51%<br /> Top unknown words in the corpus:<br /> 12 kongsan<br /> 12 pyrda<br /> 12 tulop<br /> 12 kidei<br /> 12 Wahumkhrah<br /> 12 kadei<br /> 12 Municipal<br /> 12 kol<br /> 12 pynbha<br /> 12 Bagan<br /> 12 thung<br /> 12 Executive<br /> 11 St<br /> 11 bat<br /> 11 pateng<br /> 11 shem<br /> 11 mon<br /> 11 shen<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5257 2017-05-09T22:22:50Z

<p>Nfeldba1: /* Step 19: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala - unsure<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> ==Step 20: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.90%<br /> Top unknown words in the corpus:<br /> 12 kai<br /> 12 Friday<br /> 12 nongialam<br /> 12 jingshisha<br /> 12 jongki<br /> 12 shisien<br /> 12 men<br /> 12 tnat<br /> 12 Bangladesh<br /> 12 Mobile<br /> 12 Central<br /> 12 kadei<br /> 12 ngim<br /> 12 naba<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5213 2017-05-09T06:38:17Z

<p>Nfeldba1: /* Step 18: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> ==Step 19: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.54%<br /> Top unknown words in the corpus:<br /> 13 runar<br /> 13 Mawlai<br /> 13 thep<br /> 13 kyndon<br /> 13 ïap<br /> 13 jingnang<br /> 13 bala<br /> 13 pilkrim<br /> 13 pynkhreh<br /> 13 jingstad<br /> 13 katto<br /> 13 ding<br /> 12 shakri<br /> 12 san<br /> 12 siew<br /> 12 phang<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5201 2017-05-09T06:15:45Z

<p>Nfeldba1: /* Step 17: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> ==Step 18: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 83.03%<br /> Top unknown words in the corpus:<br /> 14 kular<br /> 14 nong<br /> 14 khraw<br /> 14 sngewbha<br /> 14 Bar<br /> 14 kumne<br /> 13 pilkrim<br /> 13 KSU<br /> 13 Khristan<br /> 13 pdeng<br /> 13 wad<br /> 13 pan<br /> 13 duh<br /> 13 sengbhalang<br /> 13 longkmie<br /> 13 ap<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5198 2017-05-09T05:59:16Z

<p>Nfeldba1: /* Step 16: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.06%<br /> *Top unknown words in the corpus:<br /> *15 Circle<br /> *15 Good<br /> *15 hiar<br /> *15 synshar<br /> *15 Hato<br /> *15 klur<br /> *15 Khanna<br /> *15 kynthoh<br /> *15 katne<br /> *15 kper<br /> *15 prokram<br /> *15 jingkyrshan<br /> *15 Nongstoiñ<br /> *15 Upper<br /> *14 lut<br /> *14 kynnoh<br /> ==Step 17: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 82.60%<br /> *Top unknown words in the corpus:<br /> *14 be<br /> *14 sngewbha<br /> *14 Vinod<br /> *14 pynbna<br /> *14 rep<br /> *14 bynrap<br /> *14 hukum<br /> *14 par<br /> *14 khang<br /> *14 ïashim<br /> *14 shynrang<br /> *14 College<br /> *14 Commission<br /> *14 nongmihkhmat<br /> *14 kyrdan<br /> *14 bampong<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5196 2017-05-09T05:43:11Z

<p>Nfeldba1: /* Step 15: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> 16 shaphang<br /> 16 arngut - unsure<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> ==Step 16: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 82.06%<br /> Top unknown words in the corpus:<br /> 16 arngut<br /> 15 Circle<br /> 15 Good<br /> 15 hiar<br /> 15 synshar<br /> 15 Hato<br /> 15 klur<br /> 15 Khanna<br /> 15 kynthoh<br /> 15 katne<br /> 15 kper<br /> 15 prokram<br /> 15 jingkyrshan<br /> 15 Nongstoiñ<br /> 15 Upper<br /> 14 lut<br /> 14 kynnoh<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5195 2017-05-09T05:22:47Z

<p>Nfeldba1: /* Step 14: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> <br /> ==Step 15: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 81.56%<br /> Top unknown words in the corpus:<br /> <br /> 16 shaphang<br /> 16 arngut<br /> 16 jingpang<br /> 16 nongkyndong<br /> 16 Nongpoh<br /> 16 roi<br /> 16 Day<br /> 16 pynshai<br /> 16 lak<br /> 16 drok<br /> 16 National<br /> 16 kyrtong<br /> 16 ophisar<br /> 15 sien<br /> 15 nym<br /> 15 shakhmat<br /> 15 rung<br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5192 2017-05-09T05:06:41Z

<p>Nfeldba1: /* Step 13: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka - unsure<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> ==Step 14: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.94%<br /> Top unknown words in the corpus:<br /> 17 hynne<br /> 17 sem<br /> 17 jaidbynriew<br /> 17 beh<br /> 17 jingïalehkai<br /> 17 Lajong<br /> 17 jingrakhe<br /> 17 ïalehkai<br /> 17 masi<br /> 17 Dorbar<br /> 17 pdiang<br /> 17 katkum<br /> 16 Meet<br /> 16 kloi<br /> 16 dustur<br /> 16 kem<br /> 16 kaei<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5189 2017-05-09T04:56:08Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> <br /> ==Step 8: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 75.88%<br /> *Top unknown words in the corpus:<br /> *30 of<br /> *28 Unit<br /> *28 nyngkong<br /> *28 lynti<br /> *28 khubor<br /> *28 ktah<br /> *28 tnad<br /> *28 Mukul<br /> *28 kynthei<br /> *28 lai<br /> *27 kat<br /> *27 aiñ<br /> *27 ïakhun<br /> *27 satia<br /> *27 jingjia<br /> *27 SSA<br /> *26 Hima<br /> *26 kot<br /> *26 shi<br /> *26 K<br /> *At this point, I also decided to add all the letters in the alphabet as individual words.<br /> ==Step 9: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 77.14%<br /> *Top unknown words in the corpus:<br /> *56 EVM<br /> *26 jongka - unknown<br /> *26 lap<br /> *26 lei<br /> *25 ïaka - unknown<br /> *25 kynja<br /> *25 ophis<br /> *25 Committee<br /> *25 UDP<br /> *25 treikam<br /> *25 lait<br /> *24 Suk<br /> *24 bishar<br /> *24 im<br /> *24 ïadei<br /> *24 jingïarap<br /> *24 tit<br /> *24 riew<br /> *23 Nalor<br /> *23 shna<br /> ==Step 10: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 78.15%<br /> *Top unknown words in the corpus:<br /> *23 Election<br /> *23 sniew<br /> *23 General<br /> *23 pynban<br /> *23 kmen<br /> *22 thain<br /> *22 kyrpang<br /> *22 dawa<br /> *22 ïai<br /> *22 Pynursla<br /> *22 kdew<br /> *21 Iaiong<br /> *21 Association<br /> *21 Secondary<br /> *21 Sports<br /> *21 riti<br /> *21 phai<br /> *21 Jowai<br /> ==Step 11: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 78.91%<br /> Top unknown words in the corpus:<br /> *21 MP<br /> *21 shitom<br /> *21 burom<br /> *21 palat<br /> *21 Block<br /> *20 tyngka<br /> *20 sakhi<br /> *20 Raid<br /> *20 shuwa<br /> *20 khmih<br /> *20 juh<br /> *20 Court<br /> *20 jait<br /> *20 thong<br /> *20 pulit<br /> *20 Lyngdoh<br /> ==Step 12: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 79.62%<br /> Top unknown words in the corpus:<br /> 20 dor<br /> 20 ma<br /> 20 thong<br /> 20 man<br /> 20 heh<br /> 20 kumjuh<br /> 19 kajuh<br /> 19 nam<br /> 19 North<br /> 19 barim<br /> 19 jingmyntoi<br /> 19 Constituency<br /> 19 sngewthuh<br /> 19 hajar<br /> 19 kut<br /> 19 thoh<br /> 19 pud<br /> 19 hangne<br /> ==Step 13: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 80.31%<br /> Top unknown words in the corpus:<br /> 19 Officer<br /> 19 madan<br /> 19 jop<br /> 18 kyrpad<br /> 18 kyrwoh<br /> 18 lawei<br /> 18 Niam<br /> 18 jia<br /> 18 plie<br /> 18 haka<br /> 18 kit<br /> 18 jingeh<br /> 18 nongrim<br /> 17 vote<br /> 17 Kynrad<br /> 17 pyrshang<br /> 17 paitbah<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5143 2017-05-08T02:30:44Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> ==Step 7: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 74.78%<br /> *Top unknown words in the corpus:<br /> *31 T<br /> *31 sahlang<br /> *31 C<br /> *31 e<br /> *30 daw<br /> *30 ngin<br /> *30 party<br /> *30 poi<br /> *30 lem<br /> *29 bniah<br /> *29 katba<br /> *29 kaban<br /> *29 Kong<br /> *29 Chie<br /> *29 kynhun<br /> *29 s<br /> *29 uwei<br /> *28 dkhot<br /> *28 rai<br /> *28 Party<br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5089 2017-05-06T02:00:52Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> ==Step 6: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 73.59%<br /> *Top unknown words in the corpus:<br /> *34 daw<br /> *34 surok<br /> *34 Sangma<br /> *34 donkam<br /> *34 pyrshah<br /> *34 o<br /> *34 rukom<br /> *33 Congress<br /> *33 jing<br /> *32 dep<br /> *32 phah<br /> *32 beit<br /> *32 jingmut<br /> *32 peit<br /> *31 elekshon<br /> *31 imlang<br /> *31 un<br /> *31 sahlang<br /> *31 Jaiñtia<br /> *31 pyndonkam<br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5088 2017-05-06T01:33:56Z

<p>Nfeldba1: /* Step 4: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 5: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 72.18%<br /> *Top unknown words in the corpus:<br /> *40 kyntu<br /> *40 kyrteng<br /> *40 ïathuh<br /> *40 kino<br /> *40 lympung<br /> *39 eh<br /> *38 khamtam<br /> *38 kyntiew<br /> *38 rangbah<br /> *37 shisha<br /> *37 Trai<br /> *36 Rangbah<br /> *36 pisa<br /> *36 pule<br /> *36 kren<br /> *36 bym<br /> *35 kumno<br /> *35 Bhoi<br /> *35 ïohi<br /> *34 hok<br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5087 2017-05-06T01:33:26Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 72.18%<br /> Top unknown words in the corpus:<br /> 40 kyntu<br /> 40 kyrteng<br /> 40 ïathuh<br /> 40 kino<br /> 40 lympung<br /> 39 eh<br /> 38 khamtam<br /> 38 kyntiew<br /> 38 rangbah<br /> 37 shisha<br /> 37 Trai<br /> 36 Rangbah<br /> 36 pisa<br /> 36 pule<br /> 36 kren<br /> 36 bym<br /> 35 kumno<br /> 35 Bhoi<br /> 35 ïohi<br /> 34 hok<br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5057 2017-05-05T04:51:53Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5054 2017-05-05T04:07:51Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;<br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5050 2017-05-05T03:49:50Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> <br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=User:Nfeldba1/Final_project&diff=5049 2017-05-05T03:49:31Z

<p>Nfeldba1: Created page with &quot;==Pre-Final Project== *Number of tokenised words in the corpus: 57847 *Coverage: 57.26% *Top unknown words in the corpus: *206 kam *200 kum *179 Bah *172 kiwei *171 bynta...&quot;</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5006 2017-05-02T23:18:16Z

<p>Nfeldba1: /* Step 4: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> *Coverage: 70.14%<br /> *Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]<br /> <br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5005 2017-05-02T23:17:31Z

<p>Nfeldba1: /* Step 1: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing.<br /> <br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 70.14%<br /> Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]<br /> <br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5004 2017-05-02T23:17:12Z

<p>Nfeldba1: /* Step 4: added all the above words (and accompanying disambiguations) */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing, and I can&#039;t define kala.<br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 70.14%<br /> Top unknown words in the corpus:<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]<br /> <br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5003 2017-05-02T23:17:00Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing, and I can&#039;t define kala.<br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> ==Step 3: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 68.10%<br /> Top unknown words in the corpus:<br /> *59 kynthup<br /> *59 bapher<br /> *58 President<br /> *58 ioh<br /> *58 khynnah<br /> *58 ula<br /> *58 ei<br /> *57 School<br /> *56 lada<br /> *56 Secretary<br /> *54 khnang<br /> *54 wat<br /> *54 kumba<br /> *53 Hills<br /> *52 Dr<br /> *51 biang<br /> *50 ju<br /> ==Step 4: added all the above words (and accompanying disambiguations) ==<br /> Coverage: 70.14%<br /> Top unknown words in the corpus:<br /> *90 M<br /> *85 E<br /> *49 hadien<br /> *49 hap<br /> *49 Ïaiong<br /> *48 Myntri<br /> *48 thaiñ<br /> *47 bnai<br /> *46 ïaid<br /> *46 D<br /> *45 jingïalang<br /> *45 nongïalam<br /> *45 jur<br /> *45 kiei<br /> *44 ngut<br /> *43 lad<br /> *41 kali<br /> *41 nonghikai<br /> *41 wanrah<br /> *40 tynrai<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]<br /> <br /> <br /> *Morphologization?<br /> *ula%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;m%&gt;%&lt;past%&gt;:ula Tags ;<br /> *kala%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;sg%&gt;%&lt;f%&gt;%&lt;past%&gt;:kala Tags ;<br /> *kila%&lt;prn%&gt;%&lt;pers%&gt;%&lt;p3%&gt;%&lt;pl%&gt;%&lt;GD%&gt;%&lt;past%&gt;:kila Tags ;</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5002 2017-05-02T22:28:41Z

<p>Nfeldba1: /* Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala */</p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing, and I can&#039;t define kala.<br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> *Coverage: 66.05%<br /> *Top unknown words in the corpus (excluding M, E, and kala):<br /> *72 bun<br /> *72 hi<br /> *71 BJP<br /> *71 District<br /> *70 April<br /> *69 samla<br /> *68 ryngkat<br /> *67 liang<br /> *63 bor<br /> *63 shim<br /> *63 MLA<br /> *62 lyngba<br /> *62 sdang<br /> *62 India<br /> *60 shah<br /> *60 tylli<br /> *59 kim<br /> <br /> *aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin<br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=5001 2017-05-02T22:27:33Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations)==<br /> *Coverage: 62.96%<br /> *Top unknown words in the corpus:<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> *74 haba<br /> *74 shu<br /> I&#039;m not sure why M and E are appearing, and I can&#039;t define kala.<br /> ==Step 2: added all the above words (and accompanying disambiguations) except M, E, and kala ==<br /> Coverage: 66.05%<br /> Top unknown words in the corpus (excluding M, E, and kala):<br /> 72 bun<br /> 72 hi<br /> 71 BJP<br /> 71 District<br /> 70 April<br /> 69 samla<br /> 68 ryngkat<br /> 67 liang<br /> 63 bor<br /> 63 shim<br /> 63 MLA<br /> 62 lyngba<br /> 62 sdang<br /> 62 India<br /> 60 shah<br /> 60 tylli<br /> 59 kim<br /> <br /> [[Category:sp17_FinalProjects]]<br /> aq-covtest ling073-kha-corpus/kha.corpus.large.txt kha.automorf.bin</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=4992 2017-05-02T03:56:29Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> *Number of tokenised words in the corpus: 57847<br /> *Coverage: 57.26%<br /> *Top unknown words in the corpus:<br /> *206 kam<br /> *200 kum<br /> *179 Bah<br /> *172 kiwei<br /> *171 bynta<br /> *170 baroh<br /> *166 lah<br /> *159 pat<br /> *147 mynta<br /> *130 noh<br /> *125 paidbah<br /> *124 ne<br /> *122 ïoh<br /> *119 por<br /> *118 wan<br /> *118 Shillong<br /> *117 namar<br /> *117 Khasi<br /> *112 katei<br /> *111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations) except for Jylla==<br /> *Coverage: 62.61%<br /> *Top unknown words in the corpus:<br /> *111 Jylla<br /> *109 tang<br /> *108 ym<br /> *106 shuh<br /> *102 haduh<br /> *100 skul<br /> *98 sorkar<br /> *97 Seng<br /> *96 briew<br /> *90 M<br /> *88 jylla<br /> *88 kala<br /> *87 ri<br /> *87 lang<br /> *85 E<br /> *83 kine<br /> *82 seng<br /> *77 Meghalaya<br /> *77 tarik<br /> *74 naduh<br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=4991 2017-05-02T03:55:46Z

<p>Nfeldba1: /* Pre-Final Project */</p> <hr /> <div>==Pre-Final Project==<br /> Number of tokenised words in the corpus: 57847<br /> Coverage: 57.26%<br /> Top unknown words in the corpus:<br /> 206 kam<br /> 200 kum<br /> 179 Bah<br /> 172 kiwei<br /> 171 bynta<br /> 170 baroh<br /> 166 lah<br /> 159 pat<br /> 147 mynta<br /> 130 noh<br /> 125 paidbah<br /> 124 ne<br /> 122 ïoh<br /> 119 por<br /> 118 wan<br /> 118 Shillong<br /> 117 namar<br /> 117 Khasi<br /> 112 katei<br /> 111 Jylla<br /> ==Step 1: added all the above words (and accompanying disambiguations) except for Jylla==<br /> Coverage: 62.61%<br /> Top unknown words in the corpus:<br /> 111 Jylla<br /> 109 tang<br /> 108 ym<br /> 106 shuh<br /> 102 haduh<br /> 100 skul<br /> 98 sorkar<br /> 97 Seng<br /> 96 briew<br /> 90 M<br /> 88 jylla<br /> 88 kala<br /> 87 ri<br /> 87 lang<br /> 85 E<br /> 83 kine<br /> 82 seng<br /> 77 Meghalaya<br /> 77 tarik<br /> 74 naduh<br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=4937 2017-04-27T16:15:09Z

<p>Nfeldba1: </p> <hr /> <div>==Pre-Final Project==<br /> Number of tokenised words in the corpus: 57847<br /> Coverage: 57.26%<br /> Top unknown words in the corpus:<br /> 206 kam<br /> 200 kum<br /> 179 Bah<br /> 172 kiwei<br /> 171 bynta<br /> 170 baroh<br /> 166 lah<br /> 159 pat<br /> 147 mynta<br /> 130 noh<br /> 125 paidbah<br /> 124 ne<br /> 122 ïoh<br /> 119 por<br /> 118 wan<br /> 118 Shillong<br /> 117 namar<br /> 117 Khasi<br /> 112 katei<br /> 111 Jylla<br /> <br /> [[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Final_Project&diff=4936 2017-04-27T15:20:08Z

<p>Nfeldba1: Created page with &quot;Category:sp17_FinalProjects&quot;</p> <hr /> <div>[[Category:sp17_FinalProjects]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4898 2017-04-25T17:57:22Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> ==@cc==<br /> CC stands for coordinating conjunction.<br /> Khasi uses the word &#039;bad&#039;, meaning &#039;and&#039; most frequently as a coordinating conjunction<br /> In fact, there was no use of any of &#039;for, and, nor, but, or, yet, so&#039; in the corpus I worked with.<br /> Coordinating conjunctions in Khasi may come at the beginning of the sentence or join clauses together.<br /> Coordinating conjunctions point to the root<br /> Examples:<br /> *&quot;&lt;.&gt;&quot; <br /> **&quot;.&quot; sent @punct #35-&gt;6<br /> *&quot;&lt;Bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #1-&gt;6<br /> And<br /> *&quot;&lt;,&gt;&quot; <br /> **&quot;,&quot; cm @punct #12-&gt;18<br /> *&quot;&lt;bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #13-&gt;18<br /> [[Category:sp17_UD]]<br /> ==@det==<br /> Det stands for determiner.<br /> Khasi uses determiners in the context of articles and demonstratives<br /> These determiners modify their nouns.<br /> Examples:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #7-&gt;10<br /> *&quot;&lt;kata&gt;&quot; <br /> **&quot;kata&quot; f sg dem dist osfar @det #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;jingshai&gt;&quot; <br /> **&quot;jingshai&quot; n f @obj #10-&gt;6<br /> And<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot;<br /> **&quot;U&quot; art m sg @det #19-&gt;20<br /> *&quot;&lt;Blei&gt;&quot; <br /> **&quot;blei&quot; n m @subj #20-&gt;23<br /> ==@aux==<br /> Aux stands for auxiliary.<br /> Khasi uses aux most interestingly in the following ways:<br /> * past particles<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #5-&gt;6<br /> **&quot;&lt;pynlong&gt;&quot; <br /> ***&quot;pynlong&quot; vbser @root #6-&gt;0<br /> * continued states or actions<br /> **&quot;&lt;da&gt;&quot; <br /> ***&quot;da&quot; cont @aux #30-&gt;31<br /> **&quot;&lt;khih&gt;&quot; <br /> ***&quot;khih&quot; vblex tv @conj #31-&gt;6<br /> * the imperative &#039;let&#039;, or in Khasi, &#039;to&#039;<br /> **&quot;&lt;To&gt;&quot; <br /> ***&quot;to&quot; imp @aux #8-&gt;9<br /> **&quot;&lt;long&gt;&quot; <br /> ***&quot;long&quot; vbser @conj #9-&gt;6<br /> * A interesting case where the third person subject&#039;s personal pronoun is repeated before the verb<br /> **&quot;&lt;&lt;nowiki&gt;u&lt;/nowiki&gt;&gt;&quot; <br /> ***&quot;u&quot; prn pers p3 sg m @aux #9-&gt;8<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #10-&gt;11<br /> **&quot;&lt;khot&gt;&quot; <br /> ***&quot;khot&quot; vblex tv @root #11-&gt;0<br /> ==@case==<br /> case, as you might expect, can be used to mark case in languages with case systems, but it can also be used in languages without explicit case systems, but that have words functioning as if the case system was present. In Khasi, which doesn&#039;t explicitly have a case system, &#039;ia&#039; can be considered an accusative marker, so case is used there:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;bneng&gt;&quot; <br /> **&quot;bneng&quot; n f @obj #10-&gt;7<br /> Furthermore, words like &#039;halor&#039; - prepositions - can take case. &#039;halor&#039; means over.<br /> *&quot;&lt;halor&gt;&quot; <br /> **&quot;halor&quot; pr @case #32-&gt;34<br /> *&quot;&lt;ki&gt;&quot; <br /> **&quot;ki&quot; art GD pl @det #33-&gt;34<br /> *&quot;&lt;um&gt;&quot; <br /> **&quot;um&quot; n f @obl #34-&gt;31<br /> ==@obl==<br /> Obl stands for oblique. Oblique can be used to mark temporal adverbs:<br /> *&quot;&lt;Te&gt;&quot; <br /> ** &quot;te&quot; adv @obl #1-&gt;6<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot; <br /> ** &quot;U&quot; art m sg @det #2-&gt;3<br /> *&quot;&lt;Blei&gt;&quot; <br /> ** &quot;blei&quot; n m @nsubj #3-&gt;6<br /> As well as be the object of a case tag:<br /> *&quot;&lt;halor&gt;&quot; <br /> **&quot;halor&quot; pr @case #32-&gt;34<br /> *&quot;&lt;ki&gt;&quot; <br /> **&quot;ki&quot; art GD pl @det #33-&gt;34<br /> *&quot;&lt;um&gt;&quot; <br /> **&quot;um&quot; n f @obl #34-&gt;31</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4897 2017-04-25T17:56:48Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> ==@cc==<br /> CC stands for coordinating conjunction.<br /> Khasi uses the word &#039;bad&#039;, meaning &#039;and&#039; most frequently as a coordinating conjunction<br /> In fact, there was no use of any of &#039;for, and, nor, but, or, yet, so&#039; in the corpus I worked with.<br /> Coordinating conjunctions in Khasi may come at the beginning of the sentence or join clauses together.<br /> Coordinating conjunctions point to the root<br /> Examples:<br /> *&quot;&lt;.&gt;&quot; <br /> **&quot;.&quot; sent @punct #35-&gt;6<br /> *&quot;&lt;Bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #1-&gt;6<br /> And<br /> *&quot;&lt;,&gt;&quot; <br /> **&quot;,&quot; cm @punct #12-&gt;18<br /> *&quot;&lt;bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #13-&gt;18<br /> [[Category:sp17_UD]]<br /> ==@det==<br /> Det stands for determiner.<br /> Khasi uses determiners in the context of articles and demonstratives<br /> These determiners modify their nouns.<br /> Examples:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #7-&gt;10<br /> *&quot;&lt;kata&gt;&quot; <br /> **&quot;kata&quot; f sg dem dist osfar @det #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;jingshai&gt;&quot; <br /> **&quot;jingshai&quot; n f @obj #10-&gt;6<br /> And<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot;<br /> **&quot;U&quot; art m sg @det #19-&gt;20<br /> *&quot;&lt;Blei&gt;&quot; <br /> **&quot;blei&quot; n m @subj #20-&gt;23<br /> ==@aux==<br /> Aux stands for auxiliary.<br /> Khasi uses aux most interestingly in the following ways:<br /> * past particles<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #5-&gt;6<br /> **&quot;&lt;pynlong&gt;&quot; <br /> ***&quot;pynlong&quot; vbser @root #6-&gt;0<br /> * continued states or actions<br /> **&quot;&lt;da&gt;&quot; <br /> ***&quot;da&quot; cont @aux #30-&gt;31<br /> **&quot;&lt;khih&gt;&quot; <br /> ***&quot;khih&quot; vblex tv @conj #31-&gt;6<br /> * the imperative &#039;let&#039;, or in Khasi, &#039;to&#039;<br /> **&quot;&lt;To&gt;&quot; <br /> ***&quot;to&quot; imp @aux #8-&gt;9<br /> **&quot;&lt;long&gt;&quot; <br /> ***&quot;long&quot; vbser @conj #9-&gt;6<br /> * A interesting case where the third person subject&#039;s personal pronoun is repeated before the verb<br /> **&quot;&lt;&lt;nowiki&gt;u&lt;/nowiki&gt;&gt;&quot; <br /> ***&quot;u&quot; prn pers p3 sg m @aux #9-&gt;8<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #10-&gt;11<br /> **&quot;&lt;khot&gt;&quot; <br /> ***&quot;khot&quot; vblex tv @root #11-&gt;0<br /> ==@case==<br /> case, as you might expect, can be used to mark case in languages with case systems, but it can also be used in languages without explicit case systems, but that have words functioning as if the case system was present. In Khasi, which doesn&#039;t explicitly have a case system, &#039;ia&#039; can be considered an accusative marker, so case is used there:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;bneng&gt;&quot; <br /> **&quot;bneng&quot; n f @obj #10-&gt;7<br /> Furthermore, words like &#039;halor&#039; - prepositions - can take case. &#039;halor&#039; means over.<br /> *&quot;&lt;halor&gt;&quot; <br /> **&quot;halor&quot; pr @case #32-&gt;34<br /> *&quot;&lt;ki&gt;&quot; <br /> **&quot;ki&quot; art GD pl @det #33-&gt;34<br /> *&quot;&lt;um&gt;&quot; <br /> **&quot;um&quot; n f @obl #34-&gt;31<br /> ==@obl==<br /> Obl stands for oblique. Oblique can be used to mark temporal adverbs:<br /> *&quot;&lt;Te&gt;&quot; <br /> ** &quot;te&quot; adv @obl #1-&gt;6<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot; <br /> ** &quot;U&quot; art m sg @det #2-&gt;3<br /> *&quot;&lt;Blei&gt;&quot; <br /> ** &quot;blei&quot; n m @nsubj #3-&gt;6<br /> As well as be the object of a case tag:<br /> *&quot;&lt;halor&gt;&quot; <br /> **&quot;halor&quot; pr @case #32-&gt;34<br /> *&quot;&lt;ki&gt;&quot; <br /> **&quot;ki&quot; art GD pl @det #33-&gt;34<br /> *&quot;&lt;um&gt;&quot; <br /> **&quot;um&quot; n f @obl #34-&gt;31</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4896 2017-04-25T17:50:19Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> ==cc==<br /> CC stands for coordinating conjunction.<br /> Khasi uses the word &#039;bad&#039;, meaning &#039;and&#039; most frequently as a coordinating conjunction<br /> In fact, there was no use of any of &#039;for, and, nor, but, or, yet, so&#039; in the corpus I worked with.<br /> Coordinating conjunctions in Khasi may come at the beginning of the sentence or join clauses together.<br /> Coordinating conjunctions point to the root<br /> Examples:<br /> *&quot;&lt;.&gt;&quot; <br /> **&quot;.&quot; sent @punct #35-&gt;6<br /> *&quot;&lt;Bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #1-&gt;6<br /> And<br /> *&quot;&lt;,&gt;&quot; <br /> **&quot;,&quot; cm @punct #12-&gt;18<br /> *&quot;&lt;bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #13-&gt;18<br /> [[Category:sp17_UD]]<br /> ==det==<br /> Det stands for determiner.<br /> Khasi uses determiners in the context of articles and demonstratives<br /> These determiners modify their nouns.<br /> Examples:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #7-&gt;10<br /> *&quot;&lt;kata&gt;&quot; <br /> **&quot;kata&quot; f sg dem dist osfar @det #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;jingshai&gt;&quot; <br /> **&quot;jingshai&quot; n f @obj #10-&gt;6<br /> And<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot;<br /> **&quot;U&quot; art m sg @det #19-&gt;20<br /> *&quot;&lt;Blei&gt;&quot; <br /> **&quot;blei&quot; n m @subj #20-&gt;23<br /> ==aux==<br /> Aux stands for auxiliary.<br /> Khasi uses aux most interestingly in the following ways:<br /> * past particles<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #5-&gt;6<br /> **&quot;&lt;pynlong&gt;&quot; <br /> ***&quot;pynlong&quot; vbser @root #6-&gt;0<br /> * continued states or actions<br /> **&quot;&lt;da&gt;&quot; <br /> ***&quot;da&quot; cont @aux #30-&gt;31<br /> **&quot;&lt;khih&gt;&quot; <br /> ***&quot;khih&quot; vblex tv @conj #31-&gt;6<br /> * the imperative &#039;let&#039;, or in Khasi, &#039;to&#039;<br /> **&quot;&lt;To&gt;&quot; <br /> ***&quot;to&quot; imp @aux #8-&gt;9<br /> **&quot;&lt;long&gt;&quot; <br /> ***&quot;long&quot; vbser @conj #9-&gt;6<br /> * A interesting case where the third person subject&#039;s personal pronoun is repeated before the verb<br /> **&quot;&lt;&lt;nowiki&gt;u&lt;/nowiki&gt;&gt;&quot; <br /> ***&quot;u&quot; prn pers p3 sg m @aux #9-&gt;8<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #10-&gt;11<br /> **&quot;&lt;khot&gt;&quot; <br /> ***&quot;khot&quot; vblex tv @root #11-&gt;0<br /> ==case==<br /> case, as you might expect, can be used to mark case in languages with case systems, but it can also be used in languages without explicit case systems, but that have words functioning as if the case system was present. In Khasi, which doesn&#039;t explicitly have a case system, &#039;ia&#039; can be considered an accusative marker, so case is used there:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;bneng&gt;&quot; <br /> **&quot;bneng&quot; n f @obj #10-&gt;7<br /> Furthermore, words like &#039;halor&#039; - prepositions - can take case. &#039;halor&#039; means over.<br /> *&quot;&lt;halor&gt;&quot; <br /> **&quot;halor&quot; pr @case #18-&gt;20<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #19-&gt;20<br /> *&quot;&lt;khmat&gt;&quot; <br /> **&quot;khmat&quot; n f @obj #20-&gt;17</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4895 2017-04-25T17:45:51Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> ==cc==<br /> CC stands for coordinating conjunction.<br /> Khasi uses the word &#039;bad&#039;, meaning &#039;and&#039; most frequently as a coordinating conjunction<br /> In fact, there was no use of any of &#039;for, and, nor, but, or, yet, so&#039; in the corpus I worked with.<br /> Coordinating conjunctions in Khasi may come at the beginning of the sentence or join clauses together.<br /> Coordinating conjunctions point to the root<br /> Examples:<br /> *&quot;&lt;.&gt;&quot; <br /> **&quot;.&quot; sent @punct #35-&gt;6<br /> *&quot;&lt;Bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #1-&gt;6<br /> And<br /> *&quot;&lt;,&gt;&quot; <br /> **&quot;,&quot; cm @punct #12-&gt;18<br /> *&quot;&lt;bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #13-&gt;18<br /> [[Category:sp17_UD]]<br /> ==det==<br /> Det stands for determiner.<br /> Khasi uses determiners in the context of articles and demonstratives<br /> These determiners modify their nouns.<br /> Examples:<br /> *&quot;&lt;ia&gt;&quot; <br /> **&quot;ia&quot; dirObj @case #7-&gt;10<br /> *&quot;&lt;kata&gt;&quot; <br /> **&quot;kata&quot; f sg dem dist osfar @det #8-&gt;10<br /> *&quot;&lt;ka&gt;&quot; <br /> **&quot;ka&quot; art f sg @det #9-&gt;10<br /> *&quot;&lt;jingshai&gt;&quot; <br /> **&quot;jingshai&quot; n f @obj #10-&gt;6<br /> And<br /> *&quot;&lt;&lt;nowiki&gt;U&lt;/nowiki&gt;&gt;&quot;<br /> **&quot;U&quot; art m sg @det #19-&gt;20<br /> *&quot;&lt;Blei&gt;&quot; <br /> **&quot;blei&quot; n m @subj #20-&gt;23<br /> ==aux==<br /> Aux stands for auxiliary.<br /> Khasi uses aux most interestingly in the following ways:<br /> * past particles<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #5-&gt;6<br /> **&quot;&lt;pynlong&gt;&quot; <br /> ***&quot;pynlong&quot; vbser @root #6-&gt;0<br /> * continued states or actions<br /> **&quot;&lt;da&gt;&quot; <br /> ***&quot;da&quot; cont @aux #30-&gt;31<br /> **&quot;&lt;khih&gt;&quot; <br /> ***&quot;khih&quot; vblex tv @conj #31-&gt;6<br /> * the imperative &#039;let&#039;, or in Khasi, &#039;to&#039;<br /> **&quot;&lt;To&gt;&quot; <br /> ***&quot;to&quot; imp @aux #8-&gt;9<br /> **&quot;&lt;long&gt;&quot; <br /> ***&quot;long&quot; vbser @conj #9-&gt;6<br /> * A interesting case where the third person subject&#039;s personal pronoun is repeated before the verb<br /> **&quot;&lt;&lt;nowiki&gt;u&lt;/nowiki&gt;&gt;&quot; <br /> ***&quot;u&quot; prn pers p3 sg m @aux #9-&gt;8<br /> **&quot;&lt;la&gt;&quot; <br /> ***&quot;la&quot; past @aux #10-&gt;11<br /> **&quot;&lt;khot&gt;&quot; <br /> ***&quot;khot&quot; vblex tv @root #11-&gt;0</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4894 2017-04-25T17:34:35Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> ==CC==<br /> CC stands for coordinating conjunction.<br /> Khasi uses the word &#039;bad&#039;, meaning &#039;and&#039; most frequently as a coordinating conjunction<br /> In fact, there was no use of any of &#039;for, and, nor, but, or, yet, so&#039; in the corpus I worked with.<br /> Coordinating conjunctions in Khasi may come at the beginning of the sentence or join clauses together.<br /> Coordinating conjunctions point to the root<br /> Examples:<br /> *&quot;&lt;.&gt;&quot; <br /> **&quot;.&quot; sent @punct #35-&gt;6<br /> *&quot;&lt;Bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #1-&gt;6<br /> And<br /> *&quot;&lt;,&gt;&quot; <br /> **&quot;,&quot; cm @punct #12-&gt;18<br /> *&quot;&lt;bad&gt;&quot; <br /> **&quot;bad&quot; coocnj @cc #13-&gt;18<br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4893 2017-04-25T17:27:23Z

<p>Nfeldba1: /* Dependency Relations */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4892 2017-04-25T17:27:10Z

<p>Nfeldba1: </p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> =Dependency Relations=<br /> Add a &quot;Dependency relations&quot; section, and make a subsection for each of five dependency relations that you used at least twice in your annotation. For each relation, provide:<br /> A description of the relation, noting various ways it might be used in the language,<br /> Two examples of the relation from your corpus, preferably illustrating what you described.<br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4891 2017-04-25T17:26:17Z

<p>Nfeldba1: </p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4890 2017-04-25T17:26:03Z

<p>Nfeldba1: /* nomorph */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> <br /> <br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 87.70%<br /> | 80.33%<br /> |-<br /> |annotated2<br /> | 45.93%<br /> | 40.74%<br /> |}<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4889 2017-04-25T17:25:08Z

<p>Nfeldba1: </p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 85.66%<br /> | 78.69%<br /> |-<br /> |annotated2<br /> | 57.04%<br /> | 52.59%<br /> |}<br /> <br /> <br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 79.00%<br /> | 61.00%<br /> |-<br /> |annotated2<br /> | 77.05%<br /> | 37.70%<br /> |}<br /> <br /> <br /> <br /> annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4888 2017-04-25T17:23:45Z

<p>Nfeldba1: /* nomorph model */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 89.50%<br /> | 77.00%<br /> |-<br /> |annotated2<br /> | 72.13%<br /> | 40.98%<br /> |}<br /> <br /> ==nomorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 79.00%<br /> | 61.00%<br /> |-<br /> |annotated2<br /> | 77.05%<br /> | 37.70%<br /> |}<br /> <br /> <br /> <br /> annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4887 2017-04-25T17:23:40Z

<p>Nfeldba1: /* withmorph model */</p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 89.50%<br /> | 77.00%<br /> |-<br /> |annotated2<br /> | 72.13%<br /> | 40.98%<br /> |}<br /> <br /> ==nomorph model==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 79.00%<br /> | 61.00%<br /> |-<br /> |annotated2<br /> | 77.05%<br /> | 37.70%<br /> |}<br /> <br /> <br /> <br /> annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4886 2017-04-25T17:23:32Z

<p>Nfeldba1: </p> <hr /> <div>=Evaluation=<br /> *Number of sentences <br /> **annotated: 11<br /> **annotated2: 4<br /> <br /> *Number of forms<br /> **annotated: 244<br /> **annotated2: 135<br /> <br /> ==withmorph model==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 89.50%<br /> | 77.00%<br /> |-<br /> |annotated2<br /> | 72.13%<br /> | 40.98%<br /> |}<br /> <br /> ==nomorph model==<br /> {| class=&quot;wikitable&quot;<br /> |+Scores<br /> |-<br /> |<br /> |UAS<br /> |LAS<br /> |-<br /> |annotated<br /> | 79.00%<br /> | 61.00%<br /> |-<br /> |annotated2<br /> | 77.05%<br /> | 37.70%<br /> |}<br /> <br /> <br /> <br /> annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi&diff=4885 2017-04-25T17:20:45Z

<p>Nfeldba1: /* Developed Resources */</p> <hr /> <div>= External Resources =<br /> == Computational Resources ==<br /> I haven&#039;t been able to find any Computational Resources for Khasi except one person&#039;s keyboard layout.<br /> *Code: [https://sourceforge.net/p/khasikeyboardlayout/kha/ci/master/tree/kha]<br /> *Image: [https://a.fsdn.com/con/app/proj/khasikeyboardlayout/screenshots/Screenshot%20from%202015-01-09%2016%3A59%3A58.png/1]<br /> <br /> Furthermore, I am unsure of any licensing permissions for the keyboard or the validity of it. <br /> <br /> Update: an online Khasi-English dictionary exists: https://glosbe.com/kha/en/<br /> <br /> == Dictionaries ==<br /> === Requested from Inter-Library Loan ===<br /> *Bars, E. 1973. Khasi–English dictionary. Shillong: Don Bosco<br /> *Synrem, S. S. 2002. Ka standard dictionary: na ka Phareng Sha, ka Khasi; (English to Khasi). Shillong: H. Malngiang Synrem Jaiaw. <br /> *Singh, U. Nissor. 2006. English Khasi dictionary. New Delhi: Mittal Publications<br /> === Currently Accessible ===<br /> *Nissor Singh, U. 1906. Khasi-English dictionary. Ed. by Gurdon, P. R. T.; &amp;Dohory Ropmay, U; &amp;Hajom Kissor Singh, U. Shillong: Eastern Bengal and Assam Secretariat Press<br /> <br /> == Grammatical Descriptions ==<br /> === Requested from Inter-Library Loan ===<br /> *Henderson, Eugénie J. A. 1976. Vestiges of morphology in modern standard Khasi., Austroasiatic studies, 477-522<br /> *Nagaraja, K. S. 1979 Contraction of Khasi nouns in compounds. Indian Linguistics 40: 18–23. <br /> *Nagaraja, K. S. 1984 Reduplication in Khasi. Indo-Iranian Journal 27, no. 3: 189-200.<br /> *Roberts, H. 2000. A grammar of the Khassi language. New Delhi: Asian Educational Services.<br /> === Currently Accessible ===<br /> *Pryse, W. 1855. An introduction to the Khasia language, comprising a grammar, selections for reading, and a vocabulary. Calcutta.<br /> *Roberts, H. 1891. A grammar of the Khassi language. London: Trübner<br /> *Nagaraja, K. 1984. Compounding in Khasi. Bulletin of the Deccan College Research Institute, 43, 79-90.*Nagaraja, K. S. 1985 Khasi, a descriptive analysis (N.A.). Pune: Deccan College.<br /> *Shabong, Bashisha. 2011. Case Marker in Khasi. Language in India; Vol. 11, Issue 10<br /> <br /> == Scientific Works ==<br /> === Requested from Inter-Library Loan ===<br /> *Nissor Singh, U. 1900. Hints on the study of the Khasi language. Shillong: Ri Khasi Press.<br /> *Roy, David. 1938. The place of the Khasi in the world. Man in India 18. 122-134.<br /> *Nagaraja, K. S. 1990. Khasi phonetic reader. Mysore: Central Institute of Indian Languages.<br /> *Henderson, Eugénie J.A. 1991. Problems and Pitfalls in the Phonetic Interpretation of Khasi Orthography. Austroasiatic Languages, Essays in honour of H. L. Shorto. Ed. Jeremy H.C.S. Davidson. School of Oriental and African Studies, University of London, 61-66.<br /> === Currently Accessible ===<br /> *Henderson, Eugénie J. A. 1967. Vowel length and vowel quality in Khasi. Bulletin of the School of Asian Studies 30. 564-88.<br /> *Nagaraja K. S. 1994. Khasi dialects: A typological consideration. Mon-Khmer Studies 23. 1-10.<br /> <br /> == Corpora ==<br /> === Requested from Inter-Library Loan ===<br /> *Bareh, Hamlet. 1969. A short history of Khasi literature. Shillong: Don Bosco Press. (Hopefully will give me access to literature)<br /> *No Author Stated (ed.) 1955. Ka ktien u blei, The Holy Bible in Khasi. Calcutta.<br /> === Currently Accessible ===<br /> *http://www.mawphor.com/, an online Khasi newspaper<br /> <br /> = Developed Resources =<br /> * [https://github.swarthmore.edu/nfeldba1/ling073-kha-keyboard Keyboard Repository]<br /> * [https://github.swarthmore.edu/nfeldba1/ling073-kha-corpus (Private) Corpus Repository]<br /> * [[Khasi/Keyboard|Keyboard Wiki]]<br /> * [[Khasi/Grammar|Khasi Grammar]]<br /> * [[Khasi/Transducer|Khasi Transducer]]<br /> * [[Khasi/Disambiguation|Khasi Disambiguation]]<br /> * [[Khasi_and_Wôpanâak|Khasi and Wôpanâak]]<br /> * [[Khasi_and_Wôpanâak/ContrastiveGrammars|Contrastive Grammars]]<br /> * [[Khasi/Universal_Dependencies|Khasi Universal Dependencies]]<br /> [[Category:Khasi]] [[Category: sp17_ResourceDocumentation]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi&diff=4884 2017-04-25T17:20:34Z

<p>Nfeldba1: </p> <hr /> <div>= External Resources =<br /> == Computational Resources ==<br /> I haven&#039;t been able to find any Computational Resources for Khasi except one person&#039;s keyboard layout.<br /> *Code: [https://sourceforge.net/p/khasikeyboardlayout/kha/ci/master/tree/kha]<br /> *Image: [https://a.fsdn.com/con/app/proj/khasikeyboardlayout/screenshots/Screenshot%20from%202015-01-09%2016%3A59%3A58.png/1]<br /> <br /> Furthermore, I am unsure of any licensing permissions for the keyboard or the validity of it. <br /> <br /> Update: an online Khasi-English dictionary exists: https://glosbe.com/kha/en/<br /> <br /> == Dictionaries ==<br /> === Requested from Inter-Library Loan ===<br /> *Bars, E. 1973. Khasi–English dictionary. Shillong: Don Bosco<br /> *Synrem, S. S. 2002. Ka standard dictionary: na ka Phareng Sha, ka Khasi; (English to Khasi). Shillong: H. Malngiang Synrem Jaiaw. <br /> *Singh, U. Nissor. 2006. English Khasi dictionary. New Delhi: Mittal Publications<br /> === Currently Accessible ===<br /> *Nissor Singh, U. 1906. Khasi-English dictionary. Ed. by Gurdon, P. R. T.; &amp;Dohory Ropmay, U; &amp;Hajom Kissor Singh, U. Shillong: Eastern Bengal and Assam Secretariat Press<br /> <br /> == Grammatical Descriptions ==<br /> === Requested from Inter-Library Loan ===<br /> *Henderson, Eugénie J. A. 1976. Vestiges of morphology in modern standard Khasi., Austroasiatic studies, 477-522<br /> *Nagaraja, K. S. 1979 Contraction of Khasi nouns in compounds. Indian Linguistics 40: 18–23. <br /> *Nagaraja, K. S. 1984 Reduplication in Khasi. Indo-Iranian Journal 27, no. 3: 189-200.<br /> *Roberts, H. 2000. A grammar of the Khassi language. New Delhi: Asian Educational Services.<br /> === Currently Accessible ===<br /> *Pryse, W. 1855. An introduction to the Khasia language, comprising a grammar, selections for reading, and a vocabulary. Calcutta.<br /> *Roberts, H. 1891. A grammar of the Khassi language. London: Trübner<br /> *Nagaraja, K. 1984. Compounding in Khasi. Bulletin of the Deccan College Research Institute, 43, 79-90.*Nagaraja, K. S. 1985 Khasi, a descriptive analysis (N.A.). Pune: Deccan College.<br /> *Shabong, Bashisha. 2011. Case Marker in Khasi. Language in India; Vol. 11, Issue 10<br /> <br /> == Scientific Works ==<br /> === Requested from Inter-Library Loan ===<br /> *Nissor Singh, U. 1900. Hints on the study of the Khasi language. Shillong: Ri Khasi Press.<br /> *Roy, David. 1938. The place of the Khasi in the world. Man in India 18. 122-134.<br /> *Nagaraja, K. S. 1990. Khasi phonetic reader. Mysore: Central Institute of Indian Languages.<br /> *Henderson, Eugénie J.A. 1991. Problems and Pitfalls in the Phonetic Interpretation of Khasi Orthography. Austroasiatic Languages, Essays in honour of H. L. Shorto. Ed. Jeremy H.C.S. Davidson. School of Oriental and African Studies, University of London, 61-66.<br /> === Currently Accessible ===<br /> *Henderson, Eugénie J. A. 1967. Vowel length and vowel quality in Khasi. Bulletin of the School of Asian Studies 30. 564-88.<br /> *Nagaraja K. S. 1994. Khasi dialects: A typological consideration. Mon-Khmer Studies 23. 1-10.<br /> <br /> == Corpora ==<br /> === Requested from Inter-Library Loan ===<br /> *Bareh, Hamlet. 1969. A short history of Khasi literature. Shillong: Don Bosco Press. (Hopefully will give me access to literature)<br /> *No Author Stated (ed.) 1955. Ka ktien u blei, The Holy Bible in Khasi. Calcutta.<br /> === Currently Accessible ===<br /> *http://www.mawphor.com/, an online Khasi newspaper<br /> <br /> = Developed Resources =<br /> * [https://github.swarthmore.edu/nfeldba1/ling073-kha-keyboard Keyboard Repository]<br /> * [https://github.swarthmore.edu/nfeldba1/ling073-kha-corpus (Private) Corpus Repository]<br /> * [[Khasi/Keyboard|Keyboard Wiki]]<br /> * [[Khasi/Grammar|Khasi Grammar]]<br /> * [[Khasi/Transducer|Khasi Transducer]]<br /> * [[Khasi/Disambiguation|Khasi Disambiguation]]<br /> * [[Khasi_and_Wôpanâak|Khasi and Wôpanâak]]<br /> * [[Khasi_and_Wôpanâak/ContrastiveGrammars|Contrastive Grammars]]<br /> * [[Khasi/Universal_Dependencies|Khasi Universal_Dependencies]]<br /> [[Category:Khasi]] [[Category: sp17_ResourceDocumentation]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4883 2017-04-25T17:20:06Z

<p>Nfeldba1: </p> <hr /> <div>annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [[Category:sp17_UD]]</div>

Nfeldba1 http://wikis.swarthmore.edu/ling073/index.php?title=Khasi/Universal_Dependencies&diff=4882 2017-04-25T17:19:40Z

<p>Nfeldba1: </p> <hr /> <div>annotated and with morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 85.66%, LAS: 78.69%<br /> <br /> annotated2 and with morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 57.04%, LAS: 52.59%<br /> <br /> annotated and without morph: Parsing from gold tokenization with gold tags - forms: 244, UAS: 87.70%, LAS: 80.33%<br /> <br /> annotated2 and without morph: Parsing from gold tokenization with gold tags - forms: 135, UAS: 45.93%, LAS: 40.74%<br /> <br /> [category: sp17_UD]</div>

Nfeldba1