Difference between revisions of "Guarani and Warlpiri"

Revision as of 03:10, 20 April 2017

Resources for machine translation between Guarani and Warlpiri

Corpora

• Warlpiri Bible

• Guarani Bible

• English Bible

• Universal Declaration of Human Rights in Guarani

Developed Resources

• Corpus Repository
• Contrastive Grammar
• Guarani to Warlpiri analyzer repository
  • This repo will hold the fully functioning rule-based machine translation system.
• Warlpiri to Guarani analyzer repository
  • This repo will not be developed further.
• Lexical selection Wiki page
• Structural transfer Wiki page

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 "kuatiañe'ẽ" (Eng: letter). 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

• (wbp) muru-pinyi → (gug) mboy'u "swallow"; kuapyti "insert"
  • 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".
  • Kurdu-ngku muru-pinyi ngapa. (Eng: The child is swallowing water/grog.)
  • muru-pinyi walya (Eng: insert in the ground)

• (wbp) kirdirrpa → (gug) itakua "cave"; ka'irãi "jail"
  • 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.
  • 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.)

• (wbp) nyurltu-nyurltu → (gug) ADD HERE "confusing, garbled"; ADD HERE "tangled"
  • marnilpa - hair
• (wbp) warlu → (gug) tini "hot"; aku "angry"
  • miparrpa = face or person; yapa = person
• (wbp) yajarni → (gug) henoi "fetch/invite (someone)"; kakuaa "grow (a plant)"
  • watiya = plant

• (wbp) paarr-paarr-jankami → (gug) hapy "to burn, singe (hair or fur)"; jahéi "to hurt"
  • marnilpa - hair
• (wbp) pajirni → (gug) su'u "to bite"; hupi "to pick/gather"
  • jarntu = dog; mangarri = fruit
• (wbp) pakarli → (gug) kuatia "headdress"; kuatia "paper"
  • yangkarni = to wear