http://wikis.swarthmore.edu/ling073/api.php?action=feedcontributions&feedformat=atom&user=Nstern1
LING073 - User contributions [en]
2026-10-24T22:07:54Z
User contributions
MediaWiki 1.27.7
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Final_Project&diff=10682
Eastern Burushaski/Final Project
2019-05-15T03:29:07Z
<p>Nstern1: /* Methodology */</p>
<hr />
<div>outlines what you did, links to your code, and provides the results of your evaluation.<br />
<br />
==Arabic-Latin Orthographic Transducer of Hunza Burushaski==<br />
<br />
The Burushaski language has no consensus orthography, and literacy is low. We aim to create a transducer between two proposed orthographies which are good candidates for uptake by the Burushaski speaker community.<br />
The Latin orthography was proposed by Dr. Sadaf Munshi, curator of the North Texas University Burushaski Language Corpus. [https://digital.library.unt.edu/explore/collections/BURUS/] This orthography is used in all of her transcriptions.<br />
The Arabic orthography was proposed by Rehmat Aziz Chitrali, a linguist and researcher at Khowar Academy Chitral in Pakistan. He released a keyboard layout for PC and Mac on GitHub, [https://github.com/rachitralli/Rachitrali-Burushaski-Keyboard/blob/master/rac_burushaski/source/rac_burushaski.kmn] which we have implemented for Linux. [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-keyboard]<br />
<br />
===Methodology===<br />
Both orthographies are somewhat inconsistent or are not completely documented. We have therefore done our best to reconstruct the intentions of Dr. Munshi and Dr. Chitrali, but the orthographies we implement may differ slightly from either original. Small orthographic adjustments can easily be made to the completed transducer. <br />
To build our transducer, we used the Apertium framework.[https://wiki.apertium.org] We encoded the correspondence between the Latin and Arabic characters in our .lexc file, and wrote a number of rules to correct for inconsistencies and edge cases.<br />
We tested the functioning of the transducer by making a .yaml file [https://github.swarthmore.edu/cwillia7/ling073-bsk/blob/master/tests/ARAtests.yaml] with some expected arabic orthographic forms.<br />
<br />
===Code===<br />
The github repository for this project overall can be found at https://github.swarthmore.edu/cwillia7/ling073-bsk.<br />
<br />
===Evaluation===<br />
Despite the existence of an Arabic orthography, no corpus utilizing it could be found. To evaluate the effectiveness of our transducer, we hand-generated a small corpus of Arabic Burushaski and ran the aq-morftest script[] on the corpus to test for effectiveness and accuracy. <br />
<br />
Test Results:<br />
<br />
{| class="wikitable"<br />
|-<br />
! Test # !! pass !! fail !! total<br />
|-<br />
!0. <br />
|46<br />
|8<br />
|54<br />
|-<br />
!1. <br />
|46<br />
|16<br />
|62<br />
|-<br />
!2. <br />
| 0<br />
|12<br />
|12<br />
|-<br />
!3. <br />
| 0<br />
|12<br />
|12<br />
|-<br />
!4. <br />
| 0<br />
|24<br />
|24<br />
|-<br />
!5. <br />
| 0<br />
|24<br />
|24<br />
|-<br />
!6. <br />
| 17<br />
|26<br />
|43<br />
|-<br />
!7. <br />
| 17<br />
|25<br />
|42<br />
|-<br />
!8. <br />
| 12<br />
|17<br />
|29<br />
|-<br />
!9. <br />
| 12<br />
|14<br />
|26<br />
|-<br />
!10. <br />
| 5<br />
|0<br />
|5<br />
|-<br />
!11. <br />
| 5<br />
|32<br />
|37 <br />
|-<br />
! total<br />
| 160<br />
|210<br />
|370<br />
<br />
|}<br />
<br />
Coverage: 0.43243 or 43.24%<br />
<br />
<br />
<br />
[[Category:Sp19_FinalProjects]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10597
Eastern Burushaski and English
2019-05-14T01:20:42Z
<p>Nstern1: /* 2 lexical selection rules */</p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===5 More Morphological Elements===<br />
*-i and -u/o final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*added most common plural endings<br />
<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]<br />
<br />
===2 lexical selection rules===<br />
**ulu "in" (adposition) and "inside" (adverb)<br />
*** it̪e bulaar ulu gimo "She entered in the polo match"<br />
*** ulu hiran bai "A man was inside"<br />
**<br />
***but int̪izaam eer et̪umo.<br />
***but uyam baran</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10594
Eastern Burushaski and English
2019-05-14T00:15:46Z
<p>Nstern1: /* Additions */</p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===5 More Morphological Elements===<br />
*-i and -u/o final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*added most common plural endings<br />
<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]<br />
<br />
===2 lexical selection rules===<br />
**ulu "in" (adposition) and "inside" (adverb)<br />
*** it̪e bulaar ulu gimo "She entered in the polo match"<br />
*** ulu hiran bai "A man was inside"<br />
**</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10501
Eastern Burushaski and English
2019-04-25T14:31:51Z
<p>Nstern1: /* Additions */</p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===5 More Morphological Elements===<br />
*-i and -u/o final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*added most common plural endings<br />
<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10496
Eastern Burushaski and English
2019-04-24T20:26:52Z
<p>Nstern1: /* 5 More Morphological Elements */</p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===5 More Morphological Elements===<br />
*-i and -u/o final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10495
Eastern Burushaski and English
2019-04-24T19:36:19Z
<p>Nstern1: /* Morphological Additions */</p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===5 More Morphological Elements===<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10494
Eastern Burushaski and English
2019-04-24T19:35:39Z
<p>Nstern1: </p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
===Morphological Additions===<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
===Fix 100 Stems===<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10493
Eastern Burushaski and English
2019-04-24T19:34:02Z
<p>Nstern1: </p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation=<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10492
Eastern Burushaski and English
2019-04-24T19:33:50Z
<p>Nstern1: </p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
=Final evaluation<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10491
Eastern Burushaski and English
2019-04-24T19:21:47Z
<p>Nstern1: </p>
<hr />
<div>=Initial evaluation=<br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
*lexc and dix files (bsk and bsk-eng respectively)<br />
**910 --> 842 "UNK" tags (added tags to unknown words), so a reduction of 68<br />
**replaced instances of "." in the middle of entries with spaces (eg. "because.of" --> "because of")<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10488
Eastern Burushaski and English
2019-04-23T23:16:13Z
<p>Nstern1: /* Additions */</p>
<hr />
<div><br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-(a)n indefinite noun suffix<br />
<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10487
Eastern Burushaski and English
2019-04-23T23:16:01Z
<p>Nstern1: /* Additions */</p>
<hr />
<div><br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
*-{A}n indefinite noun suffix<br />
<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10486
Eastern Burushaski and English
2019-04-23T22:59:37Z
<p>Nstern1: </p>
<hr />
<div><br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
==Additions==<br />
*-i and -u final nouns add -y- and -w- respectively before prefixes that begin with a vowel<br />
<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10409
Eastern Burushaski and English/Structural transfer
2019-04-16T23:36:53Z
<p>Nstern1: /* after */</p>
<hr />
<div>==before==<br />
<br />
Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
==things implemented==<br />
*sentence: aa ine gane t̪ayaar baa<br />
<br />
==after==<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 40<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 40<br />
Word error rate (WER): 100.00 %<br />
Number of position-independent correct words: 0<br />
Position-independent word error rate (PER): 100.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 40<br />
Word Error Rate (WER): 100.00 %<br />
Number of position-independent correct words: 0<br />
Position-independent word error rate (PER): 100.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10408
Eastern Burushaski and English/Structural transfer
2019-04-16T23:36:10Z
<p>Nstern1: /* things implemented */</p>
<hr />
<div>==before==<br />
<br />
Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
==things implemented==<br />
*sentence: aa ine gane t̪ayaar baa<br />
<br />
==after==<br />
<br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10407
Eastern Burushaski and English/Structural transfer
2019-04-16T23:33:12Z
<p>Nstern1: </p>
<hr />
<div>==before==<br />
<br />
Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
==things implemented==<br />
<br />
==after==<br />
<br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10405
Eastern Burushaski and English/Structural transfer
2019-04-16T23:27:59Z
<p>Nstern1: </p>
<hr />
<div>==before==<br />
<br />
Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
==after==<br />
<br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10404
Eastern Burushaski and English/Structural transfer
2019-04-16T23:27:42Z
<p>Nstern1: </p>
<hr />
<div>==before==<br />
<br />
Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10191
Eastern Burushaski and English/Structural transfer
2019-04-11T13:28:34Z
<p>Nstern1: </p>
<hr />
<div>Test file: 'bsk-eng.tests.txt'<br />
Reference file 'eng.tests.txt'<br />
<br />
Statistics about input files<br />
-------------------------------------------------------<br />
Number of words in reference: 50<br />
Number of words in test: 40<br />
Number of unknown words (marked with a star) in test: <br />
Percentage of unknown words: 0.00 %<br />
<br />
Results when removing unknown-word marks (stars)<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word error rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Results when unknown-word marks (stars) are not removed<br />
-------------------------------------------------------<br />
Edit distance: 49<br />
Word Error Rate (WER): 98.00 %<br />
Number of position-independent correct words: 2<br />
Position-independent word error rate (PER): 96.00 %<br />
<br />
Statistics about the translation of unknown words<br />
-------------------------------------------------------<br />
Number of unknown words which were free rides: 0<br />
Percentage of unknown words that were free rides: 0%<br />
<br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10128
Eastern Burushaski and English/Structural transfer
2019-04-09T23:33:37Z
<p>Nstern1: </p>
<hr />
<div><br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:English]][[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Structural_transfer&diff=10127
Eastern Burushaski and English/Structural transfer
2019-04-09T23:33:10Z
<p>Nstern1: Created page with " Category:Sp19_StructuralTransferCategory:Sp19_EnglishCategory:Sp19_Eastern_Burushaski"</p>
<hr />
<div><br />
<br />
<br />
[[Category:Sp19_StructuralTransfer]][[Category:Sp19_English]][[Category:Sp19_Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Contrastive_Grammar&diff=10125
Eastern Burushaski and English/Contrastive Grammar
2019-04-09T23:11:19Z
<p>Nstern1: /* Question Particle */</p>
<hr />
<div>==bsk-eng Tests==<br />
<br />
===Ergative/Absolutive===<br />
English is a nom/acc language while Burushaski is an erg/abs language. A such, Burushaski treats the object of transitive verbs like the subject of intransitive verbs, while English treats the subjects of these two types of verbs similarly and distinguishes the object. <br />
<br />
Examples:<br />
*{{transferTest|bsk|eng|e tis amana baa. | I made a mistake.}} (#I #mistake #I# become #be.)<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa. | I am ready for him}} ( #I #that #for.the.sake.of #ready #be.)<br />
<br />
In these examples, it is evident that the Burushaski sentences contain different first-person pronouns while English uses "I" in both cases. <br />
<br />
===Verb Final===<br />
Burushaski is a SOV language, while English is SVO. This difference can be accounted or by changing the word order. <br />
<br />
* {{transferTest|bsk|eng|d̪aa šaam meey bila. | It gets dark again.}} ( #and #evening #become.IPFV #be.)<br />
* {{transferTest|bsk|eng|it̪e paad̪šaa buc̣ bila. | That is the oriental plane of the king.}} ( #that #king #oriental.plane.(tree.species) #be.)<br />
* {{transferTest|bsk|eng|ine paad̪šaa t̪alo yuu bam. | That king had seven sons.}} (#that #king #seven #sons #be.)<br />
<br />
Shown in these examples, the copula is consistently placed at the end of the sentence, while in English, it usually follows the subject.<br />
<br />
===Case Marking===<br />
Burushaski marks nouns for case, while English uses prepositions. <br />
<br />
*{{transferTest|bsk|eng|kuult̪o eer ečam|Today I will do it for him}}<br />
**{{transferMorphTest|bsk|eng|kuult̪o{{tag|adv}} e{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|sg}}{{tag|dat}} eč{{tag|v}}{{tag|p1}}{{tag|sg}}| for{{tag|pr}} prpers{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}}}}<br />
*{{transferTest|bsk|eng|ine gušpurate es baas basimi| That falcon sat on the prince}}<br />
**{{transferMorphTest|bsk|eng|in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}} gušpur{{tag|n}}{{tag|loc}} ^es{{tag|dem}} baas{{tag|n}} bas{{tag|v}}{{tag|iv}}{{tag|p3}}{{tag|sg}}{{tag|m}} that{{tag|det}}{{tag|dem}}{{tag|sg}} falcon{{tag|n}}{{tag|sg}} sit{{tag|vblex}}{{tag|past}} on{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} prince{{tag|n}}{{tag|sg}} }}<br />
<br />
===Postpositions===<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa|I am ready for him}}<br />
**{{transferMorphTest|bsk|eng|e{{tag|prn}}{{tag|pers}}{{tag|p1}}{{tag|sg}}{{tag|abs}} in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}} gane{{tag|post}} t̪ayaar{{tag|n}} b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p1}}{{tag|sg}} ready/ready{{tag|adv}}/ready{{tag|adj}}{{tag|sint}} for/for{{tag|cnjadv}}/for{{tag|pr}} prpers{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}} }}<br />
<br />
===Question Particle===<br />
<br />
*{{transferTest|bsk|eng|d̪aa it̪eer šaan e naa|And please be careful of that}}<br />
**{{transferMorphTest|bsk|eng|d̪aa{{tag|conn}} in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}{{tag|dat}} šaan{{tag|adj}} e{{tag|prn}}{{tag|pers}}{{tag|p1}}{{tag|sg}}{{tag|erg}} naa{{tag|q}}|and{{tag|cnjcoo}} please{{tag|ij}} be{{tag|vbser}}{{tag|inf}} careful{{tag|adj}} of{{tag|pr}} that{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}}}}<br />
<br />
[[Category:Sp19_ContrastiveGrammars]] [[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Contrastive_Grammar&diff=10124
Eastern Burushaski and English/Contrastive Grammar
2019-04-09T23:10:34Z
<p>Nstern1: </p>
<hr />
<div>==bsk-eng Tests==<br />
<br />
===Ergative/Absolutive===<br />
English is a nom/acc language while Burushaski is an erg/abs language. A such, Burushaski treats the object of transitive verbs like the subject of intransitive verbs, while English treats the subjects of these two types of verbs similarly and distinguishes the object. <br />
<br />
Examples:<br />
*{{transferTest|bsk|eng|e tis amana baa. | I made a mistake.}} (#I #mistake #I# become #be.)<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa. | I am ready for him}} ( #I #that #for.the.sake.of #ready #be.)<br />
<br />
In these examples, it is evident that the Burushaski sentences contain different first-person pronouns while English uses "I" in both cases. <br />
<br />
===Verb Final===<br />
Burushaski is a SOV language, while English is SVO. This difference can be accounted or by changing the word order. <br />
<br />
* {{transferTest|bsk|eng|d̪aa šaam meey bila. | It gets dark again.}} ( #and #evening #become.IPFV #be.)<br />
* {{transferTest|bsk|eng|it̪e paad̪šaa buc̣ bila. | That is the oriental plane of the king.}} ( #that #king #oriental.plane.(tree.species) #be.)<br />
* {{transferTest|bsk|eng|ine paad̪šaa t̪alo yuu bam. | That king had seven sons.}} (#that #king #seven #sons #be.)<br />
<br />
Shown in these examples, the copula is consistently placed at the end of the sentence, while in English, it usually follows the subject.<br />
<br />
===Case Marking===<br />
Burushaski marks nouns for case, while English uses prepositions. <br />
<br />
*{{transferTest|bsk|eng|kuult̪o eer ečam|Today I will do it for him}}<br />
**{{transferMorphTest|bsk|eng|kuult̪o{{tag|adv}} e{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|sg}}{{tag|dat}} eč{{tag|v}}{{tag|p1}}{{tag|sg}}| for{{tag|pr}} prpers{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}}}}<br />
*{{transferTest|bsk|eng|ine gušpurate es baas basimi| That falcon sat on the prince}}<br />
**{{transferMorphTest|bsk|eng|in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}} gušpur{{tag|n}}{{tag|loc}} ^es{{tag|dem}} baas{{tag|n}} bas{{tag|v}}{{tag|iv}}{{tag|p3}}{{tag|sg}}{{tag|m}} that{{tag|det}}{{tag|dem}}{{tag|sg}} falcon{{tag|n}}{{tag|sg}} sit{{tag|vblex}}{{tag|past}} on{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} prince{{tag|n}}{{tag|sg}} }}<br />
<br />
===Postpositions===<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa|I am ready for him}}<br />
**{{transferMorphTest|bsk|eng|e{{tag|prn}}{{tag|pers}}{{tag|p1}}{{tag|sg}}{{tag|abs}} in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}} gane{{tag|post}} t̪ayaar{{tag|n}} b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|prpers{{tag|prn}}{{tag|subj}}{{tag|p1}}{{tag|mf}}{{tag|sg}} be{{tag|vbser}}{{tag|pres}}{{tag|p1}}{{tag|sg}} ready/ready{{tag|adv}}/ready{{tag|adj}}{{tag|sint}} for/for{{tag|cnjadv}}/for{{tag|pr}} prpers{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}} }}<br />
<br />
===Question Particle===<br />
<br />
*{{transferTest|d̪aa it̪eer šaan e naa|And please be careful of that}}<br />
**{{transferMorphTest|bsk|eng|d̪aa{{tag|conn}} in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}{{tag|dat}} šaan{{tag|adj}} e{{tag|prn}}{{tag|pers}}{{tag|p1}}{{tag|sg}}{{tag|erg}} naa{{tag|q}}|and{{tag|cnjcoo}} please{{tag|ij}} be{{tag|vbser}}{{tag|inf}} careful{{tag|adj}} of{{tag|pr}} that{{tag|prn}}{{tag|dem}}{{tag|mf}}{{tag|sg}}}}<br />
<br />
[[Category:Sp19_ContrastiveGrammars]] [[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Contrastive_Grammar&diff=10123
Eastern Burushaski and English/Contrastive Grammar
2019-04-09T23:08:18Z
<p>Nstern1: </p>
<hr />
<div>==bsk-eng Tests==<br />
<br />
===Ergative/Absolutive===<br />
English is a nom/acc language while Burushaski is an erg/abs language. A such, Burushaski treats the object of transitive verbs like the subject of intransitive verbs, while English treats the subjects of these two types of verbs similarly and distinguishes the object. <br />
<br />
Examples:<br />
*{{transferTest|bsk|eng|e tis amana baa. | I made a mistake.}} (#I #mistake #I# become #be.)<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa. | I am ready for him}} ( #I #that #for.the.sake.of #ready #be.)<br />
<br />
In these examples, it is evident that the Burushaski sentences contain different first-person pronouns while English uses "I" in both cases. <br />
<br />
===Verb Final===<br />
Burushaski is a SOV language, while English is SVO. This difference can be accounted or by changing the word order. <br />
<br />
* {{transferTest|bsk|eng|d̪aa šaam meey bila. | It gets dark again.}} ( #and #evening #become.IPFV #be.)<br />
* {{transferTest|bsk|eng|it̪e paad̪šaa buc̣ bila. | That is the oriental plane of the king.}} ( #that #king #oriental.plane.(tree.species) #be.)<br />
* {{transferTest|bsk|eng|ine paad̪šaa t̪alo yuu bam. | That king had seven sons.}} (#that #king #seven #sons #be.)<br />
<br />
Shown in these examples, the copula is consistently placed at the end of the sentence, while in English, it usually follows the subject.<br />
<br />
===Case Marking===<br />
Burushaski marks nouns for case, while English uses prepositions. <br />
<br />
*{{transferTest|bsk|eng|kuult̪o eer ečam|Today I will do it for him}}<br />
**{{transferMorphTest|bsk|eng|kuult̪o{{tag|adv}} e{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|sg}}{{tag|dat}} eč{{tag|v}}{{tag|p1}}{{tag|sg}}| for{{tag|pr}} prpers{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}}}}<br />
*{{transferTest|bsk|eng|ine gušpurate es baas basimi| That falcon sat on the prince}}<br />
**{{transferMorphTest|bsk|eng|in{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}} gušpur{{tag|n}}{{tag|loc}} ^es{{tag|dem}} baas{{tag|n}} bas{{tag|v}}{{tag|iv}}{{tag|p3}}{{tag|sg}}{{tag|m}} that{{tag|det}}{{tag|dem}}{{tag|sg}} falcon{{tag|n}}{{tag|sg}} sit{{tag|vblex}}{{tag|past}} on{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} prince{{tag|n}}{{tag|sg}} }}<br />
<br />
===Postpositions===<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa|I am ready for him}}<br />
**{{transferMorphTest|bsk|eng|e{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} in{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} gane{{tag|}} t̪ayaar{{tag|}} b{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}}|prpers{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} be{{tag|}}{{tag|}}{{tag|}}{{tag|}} ready/ready{{tag|}}/ready{{tag|}}{{tag|}} for/for{{tag|}}/for{{tag|}} prpers{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} }}<br />
<br />
===Question Particle===<br />
<br />
*{{transferTest|d̪aa it̪eer šaan e naa|And please be careful of that}}<br />
**{{transferMorphTest|bsk|eng|d̪aa{{tag|}} in{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} šaan{{tag|}} e{{tag|}}{{tag|}}{{tag|}}{{tag|}}{{tag|}} naa{{tag|}}|and{{tag|}} please{{tag|}} be{{tag|}}{{tag|}} careful{{tag|}} of{{tag|}} that{{tag|}}{{tag|}}{{tag|}}{{tag|}}}}<br />
<br />
[[Category:Sp19_ContrastiveGrammars]] [[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Contrastive_Grammar&diff=10039
Eastern Burushaski and English/Contrastive Grammar
2019-04-04T13:42:56Z
<p>Nstern1: </p>
<hr />
<div>==bsk-eng Tests==<br />
<br />
===Ergative/Absolutive===<br />
English is a nom/acc language while Burushaski is an erg/abs language. A such, Burushaski treats the object of transitive verbs like the subject of intransitive verbs, while English treats the subjects of these two types of verbs similarly and distinguishes the object. <br />
<br />
Examples:<br />
*{{transferTest|bsk|eng|e tis amana baa. | I made a mistake.}} (#I #mistake #I# become #be.)<br />
*{{transferTest|bsk|eng|aa ine gane t̪ayaar baa. | I am ready for him}} ( #I #that #for.the.sake.of #ready #be.)<br />
<br />
In these examples, it is evident that the Burushaski sentences contain different first-person pronouns while English uses "I" in both cases. <br />
<br />
===Verb Final===<br />
Burushaski is a SOV language, while English is SVO. This difference can be accounted or by changing the word order. <br />
<br />
* {{transferTest|bsk|eng|d̪aa šaam meey bila. | It gets dark again.}} ( #and #evening #become.IPFV #be.)<br />
* {{transferTest|bsk|eng|it̪e paad̪šaa buc̣ bila. | That is the oriental plane of the king.}} ( #that #king #oriental.plane.(tree.species) #be.)<br />
* {{transferTest|bsk|eng|ine paad̪šaa t̪alo yuu bam. | That king had seven sons.}} (#that #king #seven #sons #be.)<br />
<br />
Shown in these examples, the copula is consistently placed at the end of the sentence, while in English, it usually follows the subject.<br />
<br />
===Case Marking===<br />
Burushaski marks nouns for case, while English uses prepositions. <br />
<br />
*{{transferTest|bsk|eng|eer{{tag|prn}}{{tag|pers}}{{tag|p3}}{{tag|sg}}{{tag|dat}}| for{{tag|pr}} him{{tag|prn}}{{tag|obj}}{{tag|p3}}{{tag|m}}{{tag|sg}}}}<br />
*{{transferTest|bsk|eng|gušpurate{{tag|n}}{{tag|loc}} | on{{tag|pr}} the{{tag|det}}{{tag|def}}{{tag|sp}} prince{{tag|n}}{{tag|sg}} }}<br />
<br />
===Postpositions===<br />
<br />
<br />
===Question Particle===<br />
<br />
<br />
[[Category:Sp19_ContrastiveGrammars]] [[Category:Eastern_Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10032
Eastern Burushaski and English
2019-04-04T13:28:25Z
<p>Nstern1: /* bsk --> eng Evaluation */</p>
<hr />
<div><br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets again dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|-<br />
|ine gušpurate es baas basimi.|| That falcon sat on the prince. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gušpur<n><loc>/prince<n><loc>$ ^es<dem>/that.[−h,.I]<dem>$ ^baas<n>/times<n>/falcon<n>$ ^bas<v><iv><p3><sg><m>/sit<v><iv><p3><sg><m>$ || #that #prince #that.[−h,.I] #times #sit.<br />
|}<br />
<br />
<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English&diff=10023
Eastern Burushaski and English
2019-04-04T12:56:03Z
<p>Nstern1: /* bsk --> eng Evaluation */</p>
<hr />
<div><br />
<br />
==Resources for machine translation between [[Eastern_Burushaski]] and English==<br />
*Apertium basic rule-based machine translation [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng/tree/master]<br />
**Corpus for MT [https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus]<br />
*Developed bilingual corpus https://github.swarthmore.edu/Ling073-sp19/ling073-bsk-eng-corpus<br />
**Corpus data courtesy of Dr. Sadaf Munshi at the University of North Texas<br />
<br />
==bsk --> eng Evaluation==<br />
Monolingual transducer finds 27 forms, misses 0. Bilingual transducer finds 135 forms, misses 0. This difference is likely due to the monolingual transducer classifying multiple forms of the same word as only one, as in "to be."<br />
<br />
{|class: "wikitable"<br />
! Burushaski Text !! English free translation !! Lexical transfer output !! Full translation output<br />
|-<br />
|tis eču bo. || She is making a mistake. || ^tis<n>/pit<n>/mistake<n>$ ^eč<v><p3><sg><f>/do.IPFV#it <v><p3><sg><f>$ ^b<cop><pres><ind><p3><sg><f>/be<cop><pres><ind><p3><sg><f>$. || #pit #do.IPFV#it #be.<br />
|-<br />
|ine paad̪šaa t̪alo yuu bam. || That king had seven sons. || ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^paad̪šaa<n>/king<n>$ ^t̪ʰalo<num><mfclx>/seven<num><mfclx>$ ^yuu<n><pl>/sons<n><pl>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #that #king #seven #sons #be.<br />
|- <br />
|kuult̪o eer ečam. || Today I will do it for him. || ^kuult̪o<n>/today<n>$ ^e<prn><pers><p1><sg><dat>/I<prn><pers><p1><sg><dat>$ ^eč<v><p1><sg>/do.IPFV#it <v><p1><sg>$. || #today #I #do.IPFV#it .<br />
|-<br />
|aa ine gane t̪ayaar baa. || I am ready for him. || ^e<prn><pers><p1><sg><abs>/I<prn><pers><p1><sg><abs>$ ^in<prn><dem><dst><sg><mf>/that<dem><dst><sg><mf>$ ^gane<post>/for.the.sake.of<post>$ ^t̪ayaar<n>/ready<n>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #that #for.the.sake.of #ready #be.<br />
|-<br />
|d̪aa it̪eer šaan e naa. || And please be careful of that. || ^d̪aa<conn>/and<conn>$ ^in<prn><dem><dst><sg><cly><dat>/that<dem><dst><sg><cly><dat>$ ^šaan<adj>/careful<adj>$ ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^naa<q>/$. || #and #that careful #I .<br />
|-<br />
|it̪e paad̪šaa buc̣ bila. || That is the oriental plane of the king. || ^in<prn><dem><dst><sg><cly><erg>/that<dem><dst><sg><cly><erg>$ ^paad̪šaa<n>/king<n>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #that #king #oriental.plane.(tree.species) #be.<br />
|-<br />
|hin paad̪šaan bam. || There was a king. || ^hin<num><mf>/one<num><mf>$ ^paad̪šaa<n><indef>/king<n><indef>$ ^b<cop><past><ind><p1><pl>/be<cop><past><ind><p1><pl>$. || #one #king #be. <br />
|-<br />
|e tis amana baa. || I made a mistake. || ^e<prn><pers><p1><sg><erg>/I<prn><pers><p1><sg><erg>$ ^tis<n>/pit<n>/mistake<n>$ ^amana<v>/I# become<v>$ ^b<cop><pres><ind><p1><sg>/be<cop><pres><ind><p1><sg>$. || #I #pit #I# become #be.<br />
|-<br />
|han buċ bila. || There is an oriental plane. || ^hin<num><clx>/one<num><clx>$ ^buc̣<n>/oriental.plane.(tree.species)<n>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #one #oriental.plane.(tree.species) #be.<br />
|-<br />
|d̪aa šaam meey bila. || It gets again dark again. || ^d̪aa<conn>/and<conn>$ ^šaam<n>/evening<n>$ ^meey<v>/become.IPFV<v>$ ^b<cop><pres><ind><p3><sg><cly>/be<cop><pres><ind><p3><sg><cly>$. || #and #evening #become.IPFV #be.<br />
|}<br />
<br />
<br />
<br />
[[Category:Eastern_Burushaski]][[Category:Sp19_TranslationPairs]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9984
Eastern Burushaski and English/Lexical selection
2019-04-02T23:09:39Z
<p>Nstern1: /* xyz → abc */</p>
<hr />
<div><br />
==bsk → eng==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* -č- "do", "make"<br />
** "Make" before nouns, "do" after adjectives.<br />
** tis eču bo "She is making a mistake"<br />
** kuult̪o eer ečam "Today I will do (it) for him<br />
* baas "times", "falcon"<br />
** "Times" following numbers, "falcon" after determiners<br />
** alt̪o baas "two times"<br />
** ine gušpurate es baas basimi "that falcon sat on the prince"<br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9983
Eastern Burushaski and English/Lexical selection
2019-04-02T23:09:26Z
<p>Nstern1: /* xyz → abc */</p>
<hr />
<div><br />
==xyz → abc==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* -č- "do", "make"<br />
** "Make" before nouns, "do" after adjectives.<br />
** tis eču bo "She is making a mistake"<br />
** kuult̪o eer ečam "Today I will do (it) for him<br />
* baas "times", "falcon"<br />
** "Times" following numbers, "falcon" after determiners<br />
** alt̪o baas "two times"<br />
** ine gušpurate es baas basimi "that falcon sat on the prince"<br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9982
Eastern Burushaski and English/Lexical selection
2019-04-02T23:07:07Z
<p>Nstern1: /* xyz → abc */</p>
<hr />
<div><br />
==xyz → abc==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* -č- "do", "make"<br />
** "Make" before nouns, "do" after adjectives.<br />
** tis eču bo "I made a mistake"<br />
** kuult̪o eer ečam "Today I will do (it) for him<br />
* baas "times", "falcon"<br />
** "Times" following numbers, "falcon" after determiners<br />
** alt̪o baas "two times"<br />
** ine gušpurate es baas basimi "that falcon sat on the prince"<br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9970
Eastern Burushaski and English/Lexical selection
2019-04-02T13:45:17Z
<p>Nstern1: </p>
<hr />
<div><br />
==xyz → abc==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* -č- "do", "make"<br />
** "Make" before nouns, "do" after adjectives.<br />
* baas "times", "falcon"<br />
** <br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9965
Eastern Burushaski and English/Lexical selection
2019-04-02T12:56:46Z
<p>Nstern1: </p>
<hr />
<div><br />
==xyz → abc==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* e: "do! (imp.)", "I (erg.)"<br />
** <br />
* -č- "do", "make"<br />
** <br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9964
Eastern Burushaski and English/Lexical selection
2019-04-02T12:55:32Z
<p>Nstern1: </p>
<hr />
<div><br />
==xyz → abc==<br />
* tis: "pit", "mistake"<br />
** "Pit" doesn't appear in our stories, and "mistake" is probably a more common word in general. Right now "pit" is the default, and we'll make "mistake" the default.<br />
* e: "do! (imp.)", "I (erg.)"<br />
** <br />
<br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski_and_English/Lexical_selection&diff=9963
Eastern Burushaski and English/Lexical selection
2019-04-02T12:48:11Z
<p>Nstern1: Created page with " Category:Sp19_LexicalSelection Category:Eastern BurushaskiCategory:English"</p>
<hr />
<div><br />
<br />
<br />
<br />
[[Category:Sp19_LexicalSelection]] [[Category:Eastern Burushaski]][[Category:English]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Disambiguation&diff=9621
Eastern Burushaski/Disambiguation
2019-02-28T14:55:27Z
<p>Nstern1: </p>
<hr />
<div>*initial level of ambiguity: 1.16<br />
<br />
<br />
<br />
[[Category:Sp19_Disambiguation]][[Category:Eastern Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Disambiguation&diff=9620
Eastern Burushaski/Disambiguation
2019-02-28T14:55:09Z
<p>Nstern1: </p>
<hr />
<div>*initial level of ambiguity: <br />
<br />
<br />
<br />
[[Category:Sp19_Disambiguation]][[Category:Eastern Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9619
Eastern Burushaski/Transducer
2019-02-28T14:54:35Z
<p>Nstern1: </p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
*204/232 (88%) analysis forms passing<br />
*176/844 (21%) coverage of corpus<br />
*102/141 (72%) initial generation<br />
*102/116 (88%) generation forms passing <br />
** one twol rule<br />
** coverage has not changed<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|ke{{tag|conj}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|kaa{{tag|conj}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|daa{{tag|conj}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || "he/she" || {{morphTest|in{{tag|pron}}{{tag|pers}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]<br />
[[Category:Eastern Burushaski]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Disambiguation&diff=9618
Eastern Burushaski/Disambiguation
2019-02-28T14:39:41Z
<p>Nstern1: </p>
<hr />
<div>stuff<br />
<br />
<br />
<br />
[[Category:Sp19_Disambiguation]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Disambiguation&diff=9617
Eastern Burushaski/Disambiguation
2019-02-28T14:37:03Z
<p>Nstern1: Created page with " Category:Sp19_Disambiguation"</p>
<hr />
<div><br />
<br />
<br />
<br />
[[Category:Sp19_Disambiguation]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9565
Eastern Burushaski/Transducer
2019-02-27T00:40:24Z
<p>Nstern1: /* initial evaluation of morphological generation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
*204/232 (88%) analysis forms passing<br />
*176/844 (21%) coverage of corpus<br />
*102/141 (72%) initial generation<br />
*102/116 (88%) generation forms passing <br />
** one twol rule<br />
** coverage has not changed<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9564
Eastern Burushaski/Transducer
2019-02-27T00:32:02Z
<p>Nstern1: /* Generator Evaluation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
*204/232 (88%) analysis forms passing<br />
*176/844 (21%) coverage of corpus<br />
*102/141 (72%) initial generation<br />
*102/116 (88%) generation forms passing<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Language&diff=9559
Eastern Burushaski/Language
2019-02-27T00:22:36Z
<p>Nstern1: /* "To be" copula forms */</p>
<hr />
<div><br />
=== Demonstrative Pronouns ===<br />
{|class="wikitable sortable"<br />
!Demonstrative pronoun !!human (m or f) !! non-human concrete !! non-human abstract/amorphous <br />
|-<br />
! this<br />
| {{morphTest|kʰine{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|sg}}{{tag|mf}}|kʰine}} || {{morphTest|kʰine{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|sg}}{{tag|clx}}|guse}} || {{morphTest|kʰine{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|sg}}{{tag|cly}}|gut̪e}}<br />
|- <br />
! that <br />
| {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}} || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}} || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|- <br />
! these <br />
| {{morphTest|kʰuwe{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|pl}}{{tag|mf}}|kʰuwe}} || {{morphTest|kʰuwe{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|pl}}{{tag|clx}}|guce}} || {{morphTest|kʰuwe{{tag|prn}}{{tag|dem}}{{tag|prx}}{{tag|pl}}{{tag|cly}}|guke}}<br />
|- <br />
!those<br />
| {{morphTest|uwe{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|pl}}{{tag|mf}}|uwe}} || {{morphTest|uwe{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|pl}}{{tag|clx}}|ice}} || {{morphTest|uwe{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|pl}}{{tag|cly}}|ike}}<br />
|} <br />
<br />
note: {{tag|mf}} is used for the class of nouns that are human, and can be either male or female, while {{tag|clx}} is used for non-human concrete and {{tag|cly}} is used for the non-human abstract/amorphous noun class.<br />
<br />
{{comment|I might give the same lemma across the three classes, so that e.g. guse's lemma is kʰine. -JNW}}<br />
<br />
=== Reduplication ===<br />
Reduplication is very productive in Burushaski, and can be used in a number of ways.<br />
<br />
==== Partial Reduplication ====<br />
Partial reduplication is only used in casual conversation. It most often applies to nouns, though Yoshioka claims that it can also be used on phrases and even clauses (p. 169). They are not clear as to the semantics of partial reduplication, and don't give any direct translations of any of their examples. Munshi's examples, on the other hand, have translations, and give a sense of a frequentative/iterative. <br />
<br />
* ''haralt̪ '''cʰu-cʰur''' manimi'' "It drizzled"<br />
** ''cʰur'' "drop"<br />
** {{morphTest|cʰur{{tag|n}}{{tag|redp}}|cʰu-cʰur}}<br />
* ''haralt̪ '''ča-čar''' manimi'' "It rained heavily"<br />
** ''čar'' "pour"<br />
** {{morphTest|čar{{tag|n}}{{tag|redp}}|ča-čar}}<br />
*''giyaase '''ǰi-ǰir''' et̪imi'' "The baby cried loudly"<br />
** ''ǰir'' "cry"<br />
** {{morphTest|ǰir{{tag|n}}{{tag|redp}}|ǰi-ǰir}}<br />
*''hilese galt̪ar '''d̪a-d̪al''' et̪imi'' "They boy dragged the tree branch"<br />
** ''d̪al'' "drag"<br />
** {{morphTest|d̪al{{tag|n}}{{tag|redp}}|d̪a-d̪al}}<br />
* ''in '''d̪a-d̪ar''' imanimi'' "He shivered"<br />
** ''d̪ar'' "shake"<br />
**{{morphTest|d̪ar{{tag|n}}{{tag|redp}}|d̪a-d̪ar}}<br />
<br />
{{comment|Reduplication isn't a semantic property, but a morphological process. Your tag should be agnostic to process and only give semantic information, like what you said about frequentative or iterative.}}<br />
<br />
==== Full Reduplication ====<br />
Full reduplication is done "without any phonological modification, such as phoneme alternation, vowel lengthening, phoneme augmentation, and so forth." (Yoshioka 2012:166) Yoshioka describes full reduplication as adding emphasis, and reduplicated words of other parts of speech often become adverbs. <br />
<br />
{|class="wikitable sortable"<br />
! Monadic !! Reduplicated !! Tagged <br />
|-<br />
| ǰotišo "small" || ǰotišo-ǰotišo "fairly small" || {{morphTest|ǰotišo{{tag|adj}}{{tag|redf}}|ǰotišo-ǰotišo}}<br />
|-<br />
| thala "slow" || thala-thala "gradually" || {{morphTest|thala{{tag|adv}}{{tag|redf}}|thala-thala}}<br />
|-<br />
| kaa "with" || kaa-kaa "close together" || {{morphTest|kaa{{tag|adj}}{{tag|redf}}|kaa-kaa}}<br />
|}<br />
Notably, reduplication can also happen across a conjunction<br />
{|class="wikitable sortable"<br />
| loto "naked" || loto-ke-loto "no cap on head" (lit. "naked and naked")<br />
|-<br />
| čʰu "naked" || čʰu-ke-čʰu "bare feet" (lit. "naked and naked")<br />
|}<br />
(wasn't sure how to tag these...)<br />
<br />
{{comment|Only use this if [mostly] productive. And again, the tag should give semantic information, not morpho-phonological. We don't use {{tag|suff_pl}} and {{tag|suff_pst}} and stuff to show that we use suffixes for plural and past, so the same should hold for reduplication.}}<br />
<br />
=== Verb stems ===<br />
Burushaski verbs are highly inflected, but verbs stems often have only two forms: a "base stem" for perfective tenses (e.g. simple past, present perfect) and a "derived stem" for imperfective tenses (e.g. future, present progressive) (Munshi in progress: 58). Examples with the verb 'to run' also from Munshi.<br />
<br />
* Perfective stem ''gaarc-''<br />
**''u '''gaarc'''uman'' "They ran" (Simple Past)<br />
*** {{morphTest|gaarc{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|pl}}|gaarcuman}}<br />
**''u '''gaarc'''am'' "They had run" (Past Perfect)<br />
*** {{morphTest|gaarc{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|pfct}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|pl}}|gaarcam}}<br />
* Imperfective stem ''gaarš-''<br />
**''u '''gaarš'''uman'' "They will run" (Future)<br />
*** {{morphTest|gaarš{{tag|v}}{{tag|iv}}{{tag|fti}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|pl}}|gaaršuman}}<br />
**''u '''gaarš'''aan'' "They run" (Present Progressive)<br />
*** {{morphTest|gaarš{{tag|v}}{{tag|iv}}{{tag|pres}}{{tag|prog}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|pl}}|gaaršaan}}<br />
**''u '''gaarš'''ume baan'' "They have been running" (Present Perfect Continuous)<br />
*** [not sure how to tag the periphrastic -- have to investigate the participle-ish thing]<br />
**''u '''gaarš'''am'' "They used to run" (Past Progressive)<br />
*** {{morphTest|gaarš{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|prog}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|pl}}|gaaršam}}<br />
<br />
{{comment|Which tags are you using to categorise the two stem types? Those tags should come close to the verb (around the transitivity tag), before any inflectional information.}}<br />
<br />
=== Causatives ===<br />
Burushaski can form causatives in three ways, increasing the valence of the verb by one.<br />
* Null derivation (just adding another pronominal prefix)<br />
** ''sabrina '''gučʰa'''mo'' "Sabrina slept"<br />
*** {{morphTest|gučʰa{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|f}}{{tag|sg}}|gučʰamo}}<br />
** ''saliime sabrina mo'''guča'''mi'' "Saleem put Sabrina to sleep"<br />
*** {{morphTest|gučʰa{{tag|v}}{{tag|tv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|m}}{{tag|sg}}{{tag|o_sg3f}}|mogučʰami}}<br />
*** no explanation of the change in aspiration -- may be a typo in source, or related to stress shift<br />
* Lengthening of vowel of object (theme) prefix<br />
** ''sabrinaa keek d̪e'''sman'''umo'' "Sabrina made the cake"<br />
*** {{morphTest|sman{{tag|v}}{{tag|tv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|f}}{{tag|o_sg3xy}}|d̪esmanumo}}<br />
*** Don't know if ''keek'' is an X or Y class word<br />
** ''karime sabrina keek d̪umoo'''sman'''imi'' "Karim caused Sabrina to make the cake"<br />
*** {{morphTest|sman{{tag|v}}{{tag|tv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|m}}{{tag|sg}}{{tag|o_sg3f}}{{tag|io_sg3xy}}|d̪umoosmanimi}}<br />
*** Don't know if ''keek'' is an X or Y class word<br />
* Prefix [s] (intransitives only)<br />
** ''hiles i'''war'''imi'' "The boy is tired"<br />
*** {{morphTest|war{{tag|v}}{{tag|iv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p3}}{{tag|sg}}|iwarimi}}<br />
** ''ǰaa hiles e'''spar'''am'' "I made the boy tired"<br />
*** {{morphTest|war{{tag|v}}{{tag|tv}}{{tag|past}}{{tag|actv}}{{tag|ind}}{{tag|p1}}{{tag|sg}}{{tag|o_sg3m}}|esparam}}<br />
<br />
(not sure how to properly tag subject vs object agreement)<br />
<br />
{{comment|You definitely do not want tags that could potentially repeat, like multiple subject agreement tags. Since multiple arguments are marked on the verb, the solution might be to use separate {{tag|s_}} and maybe {{tag|io_}} tags that correspond to your {{tag|o_}} tags.}}<br />
<br />
==="To be" copula forms ===<br />
{|class="wikitable sortable"<br />
!colspan="4"|Present Tense !! colspan="4"|Past Tense <br />
|-<br />
! colspan="2"|Singular !! colspan="2"|Plural !! colspan="2"|Singular !! colspan="2"|Plural <br />
|- <br />
!Positive !! Negative !! Positive !! Negative !! Positive !! Negative !! Positive !! Negative <br />
|- <br />
| 1 |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|baa}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|apaa}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|pl}}|baan}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p1}}{{tag|pl}}|apaan}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|bayam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p1}}{{tag|sg}}|apayam}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p1}}{{tag|pl}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p1}}{{tag|pl}}|apam}} <br />
|- <br />
| 2 |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p2}}{{tag|sg}}|baa}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p2}}{{tag|sg}}|apaa}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p2}}{{tag|pl}}|baan}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p2}}{{tag|pl}}|apaan}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p2}}{{tag|sg}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p2}}{{tag|sg}}|apam}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p2}}{{tag|pl}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p2}}{{tag|pl}}|apam}} <br />
|-<br />
| 3m |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|m}}|bai}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|m}}|apai}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|m}}|baan}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|m}}|apaan}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|m}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|m}}|apam}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|m}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|m}}|apam}} <br />
|-<br />
| 3f |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|f}}|bo}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|f}}|apo}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|f}}|baan}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|f}}|apaan}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|f}}|bom}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|f}}|apom}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|f}}|bam}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|f}}|apam}} <br />
|-<br />
| 3x |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|clx}}|bi}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|clx}}|api}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|clx}}|biye}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|clx}}|apiye}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|clx}}|bim}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|clx}}|apim}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|clx}}|bim}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|clx}}|apim}} <br />
|-<br />
| 3y |{{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|cly}}|bila}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|cly}}|api}} || {{morphTest|b{{tag|cop}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|cly}}|bica}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|pres}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|cly}}|api}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|cly}}|bilum}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|sg}}{{tag|cly}}|apim}} || {{morphTest|b{{tag|cop}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|cly}}|bicum}} || {{morphTest|b{{tag|cop}}{{tag|neg}}{{tag|past}}{{tag|ind}}{{tag|p3}}{{tag|pl}}{{tag|cly}}|apim}} <br />
<br />
|}<br />
<br />
<br />
Forms are taken from Munshi (in progress) and ''Basic Burushaski Vocabulary'' by Stephen R Willson (1999). <br />
Munshi lists the lemma for "to be" as [b], and it appears to take the past perfect verb suffixes in the past tense (Munshi example 86b) and the present progressive suffixes in the present tense (Munshi 86d). Munshi does not address the negative copula forms directly, but does list the [a-] prefix as denoting a negative (Munshi 3.1.2.4). It is possible that the [b] lemma is expressed as a [p] due to the [a-] prefix rather than being a distinct root.<br />
<br />
{{comment|Yeah, you're treating this as two distinct copula roots. If most verbs just inflect for {{tag|neg}}, then you might want to make the copula do that too, uniting "both copulas" under a single lemma.}}<br />
<br />
=== Obligatory possession ===<br />
Some nouns in Burushaski always appear with possessive markers. Yoshioka (36) cites Berger (1998a: 44), who says that there are about "150 substantives" in this class. (Yoshioka goes on to give examples that include nouns and prepositions, and it is not clear whether they count as "substantives.")<br />
Paradigms of possessed nouns are drawn from Munshi (in progress), because Yoshioka doesn't cite full forms.<br />
<br />
Words fall into (at least) two paradigms of prefixes, apparently without semantic or phonological rationale. Yoshioka also identifies a third type of possessed nouns, which they claim only includes 5 nouns, whose prefixes they list are mostly long-vowel versions of the Type-II prefixes. Yoshioka also lists possessive endings for X and Y class words, which Munshi does not cite forms for. <br />
<br />
{|class="wikitable sortable"<br />
!rowspan="2"|Pronominal prefixes of inherently possessed nouns !!colspan="2"|Type-I (e.g. -šak 'arm') !!colspan="2"|Type-II (e.g. -ċo 'same-gender sibling')<br />
|-<br />
!SG !! PL !! SG !! PL<br />
|-<br />
! 1st<br />
| {{morphTest|{{tag|px1sg}}{{tag|typ1}}{{tag|n}}šak|ašak}} || {{morphTest|{{tag|px1pl}}{{tag|typ1}}{{tag|n}}šak|mišak}} <br />
| {{morphTest|{{tag|px1sg}}{{tag|typ2}}{{tag|n}}ċo|aċo}} || {{morphTest|{{tag|px1pl}}{{tag|typ2}}{{tag|n}}ċo|meċo}}<br />
|- <br />
! 2nd<br />
| {{morphTest|{{tag|px2sg}}{{tag|typ1}}{{tag|n}}šak|gušak}} || {{morphTest|{{tag|px2pl}}{{tag|typ1}}{{tag|n}}šak|mašak}}<br />
| {{morphTest|{{tag|px2sg}}{{tag|typ2}}{{tag|n}}ċo|goċo}} || {{morphTest|{{tag|px2pl}}{{tag|typ2}}{{tag|n}}ċo|maċo}}<br />
|- <br />
! 3rd (male) <br />
| {{morphTest|{{tag|px3sgm}}{{tag|typ1}}{{tag|n}}šak|išak}} || rowspan="2"|{{morphTest|{{tag|px3pl}}{{tag|typ1}}{{tag|n}}šak|ušak}}<br />
| {{morphTest|{{tag|px3sgm}}{{tag|typ2}}{{tag|n}}ċo|eċo}} || rowspan="2"|{{morphTest|{{tag|px3pl}}{{tag|typ2}}{{tag|n}}ċo|oċo}}<br />
|- <br />
! 3rd (female)<br />
| {{morphTest|{{tag|px3sgf}}{{tag|typ1}}{{tag|n}}šak|mušak}}<br />
| {{morphTest|{{tag|px3sgf}}{{tag|typ2}}{{tag|n}}ċo|moċo}}<br />
|}<br />
<br />
=== Numerals ===<br />
Numerals are inflected for noun class (human, X, Y). For 1-3, there is a distinction between all three, but for 4-10, human and X class numerals are homophonous.<br />
<br />
{|class="wikitable sortable"<br />
!Numerals !! Human (M&F) !! X !! Y <br />
|-<br />
! 1<br />
| {{morphTest|hin{{tag|num}}{{tag|mf}}|hin}} || {{morphTest|hin{{tag|num}}{{tag|clx}}|han}} || {{morphTest|hin{{tag|num}}{{tag|cly}}|hik}}<br />
|- <br />
! 2<br />
| {{morphTest|alt̪an{{tag|num}}{{tag|mf}}|alt̪an}} || {{morphTest|alt̪an{{tag|num}}{{tag|clx}}|alt̪a}} || {{morphTest|alt̪an{{tag|num}}{{tag|cly}}|alt̪o}}<br />
|- <br />
! 3<br />
| {{morphTest|isken{{tag|num}}{{tag|mf}}|isken}} || {{morphTest|isken{{tag|num}}{{tag|clx}}|usko}} || {{morphTest|isken{{tag|num}}{{tag|cly}}|iski}}<br />
|- <br />
! 4<br />
| colspan="2"|{{morphTest|walt̪o{{tag|num}}{{tag|mfclx}}|walt̪o}} || {{morphTest|walt̪o{{tag|num}}{{tag|cly}}|walt̪i}}<br />
|- <br />
! 5<br />
| colspan="2"|{{morphTest|cʰund̪o{{tag|num}}{{tag|mfclx}}|cʰund̪o}} || {{morphTest|cʰund̪o{{tag|num}}{{tag|cly}}|cʰind̪i}}<br />
|- <br />
! 6<br />
| colspan="2"|{{morphTest|mišind̪o{{tag|num}}{{tag|mfclx}}|mišind̪o}} || {{morphTest|mišind̪o{{tag|num}}{{tag|cly}}|mišind̪i}}<br />
|- <br />
! 7<br />
| colspan="2"|{{morphTest|t̪ʰalo{{tag|num}}{{tag|mfclx}}|t̪ʰalo}} || {{morphTest|t̪ʰalo{{tag|num}}{{tag|cly}}|t̪ʰale}}<br />
|- <br />
! 8<br />
| colspan="2"|{{morphTest|alt̪ambo{{tag|num}}{{tag|mfclx}}|alt̪ambo}} || {{morphTest|alt̪ambo{{tag|num}}{{tag|cly}}|alt̪ambi}}<br />
|- <br />
! 9<br />
| colspan="2"|{{morphTest|hunčo{{tag|num}}{{tag|mfclx}}|hunčo}} || {{morphTest|hunčo{{tag|num}}{{tag|cly}}|hunti}}<br />
|- <br />
! 10<br />
| colspan="2"|{{morphTest|t̪oorumo{{tag|num}}{{tag|mfclx}}|t̪oorumo}} || {{morphTest|t̪oorumo{{tag|num}}{{tag|cly}}|t̪oorimi}}<br />
|}<br />
<br />
(talk about above 10)<br />
<br />
<br />
[[Category:Eastern_Burushaski]] [[Category:Grammar_documentation]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9541
Eastern Burushaski/Transducer
2019-02-26T14:05:17Z
<p>Nstern1: /* initial evaluation of morphological generation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
*204/232 (88%) analysis forms passing<br />
*176/844 (21%) coverage of corpus<br />
*102/141 (72%) initial generation<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9538
Eastern Burushaski/Transducer
2019-02-26T14:02:43Z
<p>Nstern1: /* initial evaluation of morphological generation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
204/232 (88%) analysis forms passing<br />
176/844 (21%) coverage of corpus<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9535
Eastern Burushaski/Transducer
2019-02-26T13:59:09Z
<p>Nstern1: /* initial evaluation of morphological generation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
88% of analysis forms passing<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9534
Eastern Burushaski/Transducer
2019-02-26T13:53:45Z
<p>Nstern1: </p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
==Analyzer Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9533
Eastern Burushaski/Transducer
2019-02-26T13:53:15Z
<p>Nstern1: </p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Generator Evaluation==<br />
===initial evaluation of morphological generation===<br />
<br />
== Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9426
Eastern Burushaski/Transducer
2019-02-21T15:37:25Z
<p>Nstern1: /* Evaluation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Evaluation==<br />
<br />
Passes 88 tests<br />
13% corpus coverage, with 844 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
After addition of 3 words from commonwords.yaml, coverage is 21%<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9415
Eastern Burushaski/Transducer
2019-02-21T15:02:23Z
<p>Nstern1: /* Evaluation */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Evaluation==<br />
<br />
Passes 88 tests<br />
7.08% corpus coverage, with 904 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
commonwords.yaml, 3 tests pass<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1
http://wikis.swarthmore.edu/ling073/index.php?title=Eastern_Burushaski/Transducer&diff=9413
Eastern Burushaski/Transducer
2019-02-21T14:58:27Z
<p>Nstern1: /* Top Unknown Words */</p>
<hr />
<div>==Code==<br />
Repo on github [https://github.swarthmore.edu/cwillia7/ling073-bsk]<br />
<br />
==Evaluation==<br />
<br />
Passes 88 tests<br />
7.08% corpus coverage, with 904 tokenised words.<br />
===Top Unknown Words ===<br />
<br />
{|class="wikitable"<br />
!Word !! Occurrences !! Gloss !! Tags <br />
|-<br />
| ke || 47 || "and" || {{morphTest|{{tag|unk}}|ke}}<br />
|- <br />
| ine || 19 || "that" (human) ||{{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|mf}}|ine}}<br />
|- <br />
| kaa || 17 || "with" || {{morphTest|{{tag|unk}}|kaa}}<br />
|- <br />
| daa || 16 || "and" || {{morphTest|{{tag|unk}}|daa}}<br />
|-<br />
| it̪e || 14 || "that" (class y) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|cly}}|it̪e}}<br />
|-<br />
| inar || 12 || || {{morphTest|{{tag|unk}}|inar}}<br />
|-<br />
| e || 10 || "me" (abs) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|abs}}|e}}<br />
|-<br />
| nuse || 9 || || {{morphTest|{{tag|unk}}|nuse}}<br />
|-<br />
| in || 8 || || {{morphTest|{{tag|unk}}|in}}<br />
|-<br />
| u || 8 || || {{morphTest|{{tag|unk}}|u}}<br />
|-<br />
| besan || 7 || || {{morphTest|{{tag|unk}}|besan}}<br />
|-<br />
| yuu || 7 || || {{morphTest|{{tag|unk}}|yuu}}<br />
|-<br />
| a || 7 || || {{morphTest|{{tag|unk}}|a}}<br />
|-<br />
| t̪ačume || 7 || || {{morphTest|{{tag|unk}}|t̪ačume}}<br />
|-<br />
| aa || 6 || "me" (erg/gen) || {{morphTest|a{{tag|prn}}{{tag|p1}}{{tag|sg}}{{tag|erg}}|aa}}<br />
|-<br />
| ečam || 6 || || {{morphTest|{{tag|unk}}|ečam}}<br />
|-<br />
| but || 6 || || {{morphTest|{{tag|unk}}|but}}<br />
|-<br />
| senasar || 6 || || {{morphTest|{{tag|unk}}|senasar}}<br />
|-<br />
| bas || 6 || || {{morphTest|{{tag|unk}}|bas}}<br />
|-<br />
| ise || 6 || "that" (class x) || {{morphTest|ine{{tag|prn}}{{tag|dem}}{{tag|dst}}{{tag|sg}}{{tag|clx}}|ise}}<br />
|} <br />
<br />
<br />
Lexccounter: Our corpus contains # stems.<br />
<br />
==Notes==<br />
Tests that currently do not work have not been implemented yet. Implemented tests work, but may need further refinement (archiphonemes added, etc). <br />
<br />
<br />
[[Category:Sp18 Transducers]]</div>
Nstern1