Difference between revisions of "Guarani and Warlpiri"

From LING073
Jump to: navigation, search
(→‎wbp → gug)
(→‎gug → wbp)
 
(40 intermediate revisions by 2 users not shown)
Line 21: Line 21:
  
 
==Lexical Selection==
 
==Lexical Selection==
 +
* See Lexical Selection page linked above for more detail
 +
 
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
 
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
 
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
 
* (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
Line 85: Line 87:
 
==Final Evaluation==
 
==Final Evaluation==
  
−
===100 more stems===
+
===gug → wbp and wbp → gug===
 +
====100 more stems====
 
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.
 
Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.
  
−
===3 new lexical selection rules===
+
===gug → wbp===
−
====gug → wbp====
 
−
* (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
 
−
** Rule: Select "lirra" (Eng: voice) as the translation of "ahy'o" when it is followed by "tyapu" (Eng: loud) or "kirirĩ" (Eng: quiet). Select "ngukarna" (Eng: throat) as the translation of "ahy'o" when it is followed by "rasy" (Eng: sore). Otherwise, select "lirra" as the default.
 
−
** Ha'e ahy'o tyapu ("His/Her loud voice")
 
−
** Ha'e oguereko ahy'o rasy ("He/she/they have a sore throat")
 
−
 
−
* (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
 
−
** Rule: Select "japirdimi" (Eng: collar) as the translation of "ajúra" when it is followed by color words such as "pytã" (Eng: red), "chovy" (Eng: blue) or "aky" (Eng: green). Select "waninja" (Eng: neck) as the translation of "ajúra" when it is followed by "puku" (Eng: long) or "koli" (Eng: short). Otherwise, select "waninja" as the default.
 
−
** Ajúra puku ("long neck")
 
−
** Ajúra pytã ("red collar")
 
  
 +
====6 new lexical selection rules====
 
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
 
* (gug) akã → (wbp) jurru "head"; payarrpa "hill"
 +
** Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.
 +
 
* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
 
* (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
−
* (gug) henyhẽ → (wbp) ??? "full"; ??? "pregnant"
+
** Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.
 +
 
 +
* (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
 +
** Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.
 +
 
 +
* (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
 +
** Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.
 +
 
 +
* (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
 +
** Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.
 +
 
 +
* (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
 +
** Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.
  
−
====wbp → gug====
+
====6 additions to the morphology====
−
* (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
+
*Added numeral analysis:
−
** Rule: select "mboy'u" if "muru-pinyi" is followed by food or drink words: "ngapa" (water/grog), "pama" (liquor), "jirnarri" (food), and "mangarri" (vegetable). In other cases, select "kuapyti".
+
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
−
**Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
+
**the -pala ending distinguishes them as number words, but it is not always necessary
−
**muru-pinyi walya (Eng: insert in the ground)
+
**"rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
 +
**"rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$
 +
 
 +
*Added adverb analysis:
 +
**"nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$
 +
 
 +
*Added elative/source case for verb auxiliaries :
 +
**"kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$
  
−
* (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
+
*Added inceptive aspect for verbs:
−
** Rule: We couldn't come up with a good way to solve this problem. We decided to select "itakua" as the default, because it appears to be more common.
+
**"pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$
−
**Kurdu-ngku nyanyi kirdirrpa. (Eng: The child is looking for the cave.)
 
−
**Wati-ngku jarda-jarrimi kirdirrpa-rla (Eng: The man sleeps in the jail.)
 
  
 +
*Added possessive marker "nyanu" for nouns:
 +
**"kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$
  
−
* (wbp) juka → (gug) asuka "sugar"; aichémemby "cousin"
+
*Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
−
* (wbp) warlu → (gug) tini "hot"; aku "angry"
+
**echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$
−
* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
 
  
−
===Morphology additions===
+
<!--
 +
-----------------------------------
 
*Improved pronomial analysis:
 
*Improved pronomial analysis:
 
**Before: "<ngaju>"
 
**Before: "<ngaju>"
Line 135: Line 150:
 
*After:  
 
*After:  
 
**"<ngaju>"
 
**"<ngaju>"
−
 
−
*Added numeral analysis:
 
−
**Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
 
−
**the -pala ending distinguishes them as number words, but it is not always necessary
 
−
**echo "rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
 
−
**echo "rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$
 
−
 
  
  
−
 
−
-----------------------------------
 
 
*Clitics
 
*Clitics
 
** (wbp) -yijala  cl. also, too, likewise.
 
** (wbp) -yijala  cl. also, too, likewise.
Line 169: Line 175:
 
*-wiyi (first)
 
*-wiyi (first)
 
*-wana  ns. along, alongside, beside.
 
*-wana  ns. along, alongside, beside.
 +
-->
  
−
===Disambiguation===
+
<!--
 +
====4 new disambiguation rules====
 
*Number vs Noun (e.g. rdaka = hand or five), has the number marker -pala
 
*Number vs Noun (e.g. rdaka = hand or five), has the number marker -pala
 
*Manu = cnjcoo vs v tv past?
 
*Manu = cnjcoo vs v tv past?
 +
*Kuja = "ka" vaux rel subj3sg OR kuja = kuja  cj. relative pronoun, what, which, that, who.
 +
**Kuja = "ka" vaux rel subj3sg OR kuja = kuja  cj. relative pronoun, what, which, that, who.
 +
**Ngula = "ka" vaux rel subj3sg OR kuja = kuja  cj. relative pronoun, what, which, that, who. Find by searching AUX:COMP in new dictionary
 +
-->
 +
 +
===wbp → gug===
 +
====6 new lexical selection rules====
 +
* (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
 +
** Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.
 +
 +
* (wbp) warlu → (gug) tini "hot"; aku "angry"
 +
** Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.
 +
 +
* (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
 +
** Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.
 +
 +
* (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
 +
** Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.
 +
 +
* (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
 +
** Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.
 +
 +
* (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
 +
** Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.
 +
 +
 +
====4 new twol rules====
 +
*Nasal harmony on dative suffix -pe:
 +
**-pe now properly changes to -me when before a nasal vowel.
 +
**Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
 +
  echo "havõme" | apertium -d . gug-morph
 +
  ^havõme/havõ<n><sg><dat>$^./.<sent>$
  
 +
*Nasal harmony on accusative suffix -ve:
 +
**-ve now properly changes to -me on accusative forms of pronouns
 +
**Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
 +
  echo "peẽme" | apertium -d . gug-morph
 +
  ^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$
 +
 +
*Stress on accusative forms of pronouns:
 +
**The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
 +
**Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
 +
  echo "chéve" | apertium -d . gug-morph
 +
  ^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$
 +
 +
*Nasal harmony on reflexive prefix je- :
 +
**je- now properly changes to -ñe when before a nasal.
 +
**Ex: ñeñapytĩ (“to tie”).
 +
  echo "oñeñapytĩ" | apertium -d . gug-morph
 +
  ^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><nowiki><ref></nowiki>$^./.<sent>$
 +
 +
 +
===Tests results===
 +
 +
====gug====
 +
*Precision and recall:
 +
**Results:
 +
  precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
 +
  Totals: 89 tp, 87 fp, 0 tn, 19 fn
 +
  Precision: 82.40741%
 +
  Recall: 50.56818%
 +
 +
*Coverage over large corpus:
 +
**Results:
 +
  aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
 +
  Number of tokenised words in the corpus: 522284
 +
  Coverage: 28.96%
 +
 +
*Number of stems in transducer: ~270 (didn't count by hand)
 +
 +
====wbp====
 +
*Precision and recall:
 +
**Results:
 +
  precisionRecall ../ling073-wbp-corpus/wbp.annotated.basic.txt corpus.out.txt
 +
Totals: 199 tp, 5 fp, 0 tn, 6 fn
 +
Precision: 97.54902%
 +
Recall: 97.07317%
 +
 +
*Coverage over large corpus:
 +
**Results:
 +
aq-covtest ../ling073-wbp-corpus/wbp.corpus.large.txt wbp.automorf.bin
 +
Number of tokenised words in the corpus: 18427
 +
Coverage: 51.26%
 +
 +
*Number of stems in transducer: ~250
 +
 +
====wbp → gug====
 +
*WER and PER
 +
  Number of words in reference: 76
 +
  Number of words in test: 69
 +
  Number of unknown words (marked with a star) in test: 45
 +
  Percentage of unknown words: 65.22 %
 +
  Word error rate (WER): 100.00 %
 +
  Position-independent word error rate (PER): 94.74 %
 +
*Proportion of stems translate correctly in longer: 31/71 = 40.8%
 +
 +
Unsure... Need wbp.longer.txt to test in longer and large
 +
 +
====gug → wbp====
 +
*WER and PER over gug.longer.txt
 +
  Number of words in reference: 72
 +
  Number of words in test: 81
 +
  Number of unknown words (marked with a star) in test: 44
 +
  Percentage of unknown words: 54.32 %
 +
  Word error rate (WER): 112.50.00 %
 +
  Position-independent word error rate (PER): 108.33 %
 +
*Proportion of stems translate correctly in longer: (81-44 / 81) = 37/81 = 45.7%
 +
*Trimmed coverage and number of tokens in longer and large corpora
 +
aq-covtest ../ling073-gug-wbp-corpus/gug.longer.txt gug-wbp.automorf.bin
 +
**Number of tokenised words in the longer corpus: 97
 +
**Coverage: 50.52%
 +
 +
 +
aq-covtest ../ling073-gug-wbp-corpus/gug.corpus.large.txt gug-wbp.automorf.bin
 +
**Number of tokenised words in the large corpus: 501127
 +
**Coverage: 24.74%
  
 
[[Category:Sp17_TranslationPairs]]
 
[[Category:Sp17_TranslationPairs]]

Latest revision as of 01:42, 8 May 2017

Resources for machine translation between Guarani and Warlpiri

Corpora

Developed Resources

Lexical Selection

  • See Lexical Selection page linked above for more detail
  • (gug) ahy'o → (wbp) ngukarna "throat"; lirra "voice"
  • (gug) ha'anga → (wbp) japirdimi "threaten"; walaparrirni "imitate"
  • (gug) ajúra → (wbp) japirdimi "collar"; waninja "neck"
  • (wbp) rdaka → (gug) avatisoka "hand"; po "five"
  • (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"

Initial Evaluation

wbp → gug evaluation

Results when running on tests

  • Total number of words: 14
  • Total number of unknown words: 4
  • Percentage of unknown words: 28.57%
  • Percentage of stems translated correctly: 71.43%

When removing unknown words:

  • WER = 78.57%
  • PER = 78.57%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%

Results when running on sentences (corpus)

  • Total number of words: 58
  • Total number of unknown words: 68
  • Percentage of unknown words: 84.45%
  • Percentage of stems translate correctly: 15.52%

When removing unknown words:

  • WER = 22.41%
  • PER = 22.41%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%


gug → wbp evaluation

Results when running on tests

  • Total number of words: 13
  • Total number of unknown words: 0
  • Percentage of unknown words: 0%
  • Percentage of stems translated correctly: 100%

When removing unknown words:

  • WER = 92.86%
  • PER = 92.86%

When unknown words are not removed:

  • WER = 92.86%
  • PER = 92.86%

Results when running on sentences (corpus)

  • Total number of words: 66
  • Total number of unknown words: 60
  • Percentage of unknown words: 90.9%
  • Percentage of stems translated correctly: 9.09%

When removing unknown words:

  • WER = 0.0%
  • PER = 0.0%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%

Final Evaluation

gug → wbp and wbp → gug

100 more stems

Added 100 more stems (mostly nouns, verbs, and adjectives) to the bilingual and monolingual dictionaries.

gug → wbp

6 new lexical selection rules

  • (gug) akã → (wbp) jurru "head"; payarrpa "hill"
    • Rule: Select "jurru" (Eng: head) as the translation of "akã" when it is preceded by "ha'e" (Eng: his/her). Otherwise, select "payarrpa" as the default.
  • (gug) asu → (wbp) jampu "left"; jampu-karra "left-handed"
    • Rule: Select "jampu-karra" (Eng: left-handed) as the translation of "asu" when it is followed by person words such as "ava" (Eng: person) or "kuña" (Eng: woman) or "mitã" (Eng: child). Otherwise, select "jampu" (Eng: left) as the default.
  • (gug) henyhẽ → (wbp) jaka-ngalya "full"; ngayarrka "pregnant"
    • Rule: Select "ngayarrka" (Eng: pregnant) as the translation of "henyhẽ" when it is followed/preceded by "kuña" (Eng: woman) or other words describing female people. Otherwise, select "jaka-ngalya" (Eng: full) as the default.
  • (gug) mongúi → (wbp) kijirni "to throw"; pata-karrimi "to fall"
    • Rule: Select "kijirni" (Eng: to throw) as the translation of "mopẽ" when it is followed by "ita" (Eng: rock) or "apu'a" (Eng: ball). Otherwise, select "pata-karrimi" as the default.
  • (gug) moha'anga → (wbp) pantirni "to draw"; jarntirni "to carve"
    • Rule: Select "pantirni" (Eng: to draw) as the translation of "moha'anga" when it is followed by "ha'anga" (Eng: drawing). Otherwise, select "jarntirni" as the default.
  • (gug) mbogyapy → (wbp) pipa-kurra-mani "to write"; nyinanja-wantimi "to sit down"
    • Rule: Select "pipa-kurra-mani" (Eng: to write) as the translation of "mbogyapy" when it is followed by "aranduka" (Eng: book). Otherwise, select "nyinanja-wantimi" as the default.

6 additions to the morphology

  • Added numeral analysis:
    • Several number words in Warlpiri also have meanings as nouns (e.g. rdaka can mean "hand" or "five")
    • the -pala ending distinguishes them as number words, but it is not always necessary
    • "rdaka-pala": ^rdaka-pala/rdaka<num>$^./.<sent>$
    • "rdaka": ^rdaka/rdaka<num>/rdaka<n><sg><abs>$^./.<sent>$
  • Added adverb analysis:
    • "nyurruwiyi: ^nyurruwiyi/nyurruwiyi<adv>$^./.<sent>$
  • Added elative/source case for verb auxiliaries :
    • "kajangka": ^kajangka/ka<vaux><src><subj3sg>$^./.<sent>$
  • Added inceptive aspect for verbs:
    • "pakarnunjunu": ^pakarnunjunu/pakarni<v><tv><past><inc>$^./.<sent>$
  • Added possessive marker "nyanu" for nouns:
    • "kaja-nyanu-rlu": ^kaja-nyanu-rlu/kaja<n><pl><poss><erg>$^./.<sent>$
  • Added the topicalizing particle grammatical marker for nouns. -ja is used to mark known information or to indicate the topic, although sometimes it has no function.
    • echo "kurdukuju": ^kurdukuju/kurdu<n><sg><dat><top>$^./.<sent>$


wbp → gug

6 new lexical selection rules

  • (wbp) nyurltu-nyurltu → (gug) apañuãi "confusing, garbled"; apokytã "tangled"
    • Rule: select "apokytã" if "nyurltu-nyurltu" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "apañuãi" as the default.
  • (wbp) warlu → (gug) tini "hot"; aku "angry"
    • Rule: select "aku" if "warlu" is followed by the Warlpiri word "miparrpa" (face) or "yapa" (person). In other cases, select "tini" as the default.
  • (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
    • Rule: select "kakuaa" if "yajarni" is followed by the Warlpiri word "watiya" (plant). In other cases, select "henoi" as the default.
  • (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
    • Rule: select "hapy" if "paarr-paarr-jankami" is followed by the Warlpiri word "marnilpa" (hair). In other cases, select "jahéi" as the default.
  • (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
    • Rule: select "hupi" if "pajirni" is followed by the Warlpiri word "mangarri" (fruit). In other cases, select "su'u" as the default.
  • (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
    • Rule: select "kuatia" if "pakarli" is preceded by the Warlpiri word "yangkarni" (to wear). In other cases, select "kuatia" as the default.


4 new twol rules

  • Nasal harmony on dative suffix -pe:
    • -pe now properly changes to -me when before a nasal vowel.
    • Ex: havõ (soap). Suffix is regularly -pe, but now becomes -me
 echo "havõme" | apertium -d . gug-morph
 ^havõme/havõ<n><sg><dat>$^./.<sent>$
  • Nasal harmony on accusative suffix -ve:
    • -ve now properly changes to -me on accusative forms of pronouns
    • Ex: peẽ (second person plural pronoun). Suffix is regularly -ve, but now becomes -me
 echo "peẽme" | apertium -d . gug-morph
 ^peẽme/peẽ<prn><pers><p2><sg><acc>$^./.<sent>$
  • Stress on accusative forms of pronouns:
    • The e at the end of pronouns should be stressed (é) when followed by the acc suffix -ve
    • Ex: che (first person singular pronoun). With suffix -ve, becomes chéve
 echo "chéve" | apertium -d . gug-morph
 ^chéve/che<prn><pers><p1><sg><acc>$^./.<sent>$
  • Nasal harmony on reflexive prefix je- :
    • je- now properly changes to -ñe when before a nasal.
    • Ex: ñeñapytĩ (“to tie”). 
 echo "oñeñapytĩ" | apertium -d . gug-morph
 ^oñeñapytĩ/ñapytĩ<v><tv><ar><pres><p3><sp><ref>$^./.<sent>$


Tests results

gug

  • Precision and recall:
    • Results:
 precisionRecall ../corpus/ling073-gug-corpus/ling073-gug-corpus/gug.annotated.basic.txt ../bootstrap/ling073-gug/corpus.out.txt
 Totals: 89 tp, 87 fp, 0 tn, 19 fn
 Precision: 82.40741%
 Recall: 50.56818%
  • Coverage over large corpus:
    • Results:
 aq-covtest ~/Source/corpus/ling073-gug-corpus/ling073-gug-corpus/gug.corpus.large.txt gug.automorf.bin
 Number of tokenised words in the corpus: 522284
 Coverage: 28.96%
  • Number of stems in transducer: ~270 (didn't count by hand)

wbp

  • Precision and recall:
    • Results:
 precisionRecall ../ling073-wbp-corpus/wbp.annotated.basic.txt corpus.out.txt

Totals: 199 tp, 5 fp, 0 tn, 6 fn Precision: 97.54902% Recall: 97.07317%

  • Coverage over large corpus:
    • Results:
aq-covtest ../ling073-wbp-corpus/wbp.corpus.large.txt wbp.automorf.bin

Number of tokenised words in the corpus: 18427 Coverage: 51.26%

  • Number of stems in transducer: ~250

wbp → gug

  • WER and PER
 Number of words in reference: 76
 Number of words in test: 69
 Number of unknown words (marked with a star) in test: 45
 Percentage of unknown words: 65.22 %
 Word error rate (WER): 100.00 %
 Position-independent word error rate (PER): 94.74 %
  • Proportion of stems translate correctly in longer: 31/71 = 40.8%

Unsure... Need wbp.longer.txt to test in longer and large

gug → wbp

  • WER and PER over gug.longer.txt
 Number of words in reference: 72
 Number of words in test: 81
 Number of unknown words (marked with a star) in test: 44
 Percentage of unknown words: 54.32 %
 Word error rate (WER): 112.50.00 %
 Position-independent word error rate (PER): 108.33 %
  • Proportion of stems translate correctly in longer: (81-44 / 81) = 37/81 = 45.7%
  • Trimmed coverage and number of tokens in longer and large corpora
aq-covtest ../ling073-gug-wbp-corpus/gug.longer.txt gug-wbp.automorf.bin
**Number of tokenised words in the longer corpus: 97
**Coverage: 50.52%



aq-covtest ../ling073-gug-wbp-corpus/gug.corpus.large.txt gug-wbp.automorf.bin
**Number of tokenised words in the large corpus: 501127
**Coverage: 24.74%
Retrieved from "http://wikis.swarthmore.edu/ling073/index.php?title=Guarani_and_Warlpiri&oldid=5137"