Difference between revisions of "Evenki and English"
From LING073
(→Sentence Translation) |
(→Sentence Translation) |
||
| Line 109: | Line 109: | ||
|} | |} | ||
| − | Note: Many of the words with stems entered into the bilingual dictionary are not translating despite being in both the monolingual and bilingual dictionaries (ie, based on our entries to apertium-evn.evn.lexc "Сӣ ӈӣ?" should be translating to "you where from?" or "you no-one" accounting for lack of disambiguation). We are unsure why although it seems to be an orthography issue with the transducer we pulled from apertium. We have been unable to resolve this problem at this time despite working with a TA for several hours. | + | Note: Many of the words with stems entered into the bilingual dictionary are not translating despite being in both the monolingual and bilingual dictionaries (ie, based on our entries to apertium-evn.evn.lexc "Сӣ ӈӣ?" should be translating to "you where from?" or "you no-one" accounting for lack of disambiguation). We are unsure why although it seems to be an orthography issue with the transducer we pulled from apertium. We have been unable to resolve this problem at this time despite working with a TA for several hours. This has lead to artificially poor performance from our whole RBMT system pipeline. |
=== Additions === | === Additions === | ||
Revision as of 13:08, 11 May 2023
Resources for translation between Evenki and English.
Contents
External Resources
Developed Resources
EVN → ENG Initial Evaluation
Monolingual Transducer Coverage
- English Coverage
TOP UNKNOWN WORDS:
coverage: 129 / 129 (1) remaining unknown forms: 0
- Evenki Coverage
TOP UNKNOWN WORDS:
4 ^Ңи/*Ңи$
4 ^вэл/*вэл$
1 ^эңэсит/*эңэсит$
1 ^умунупкиттула/*умунупкиттула$
1 ^турӣнмумачин/*турӣнмумачин$
1 ^са̄рича̄нинду/*са̄рича̄нинду$
1 ^нуңан/*нуңан$
1 ^мэ̄нңи/*мэ̄нңи$
1 ^кэсэгӣчивунду/*кэсэгӣчивунду$
1 ^куңака̄н/*куңака̄н$
1 ^илэчэврэви/*илэчэврэви$
1 ^ӣвувра/*ӣвувра$
1 ^гражданствоват/*гражданствоват$
1 ^государстваду/*государстваду$
1 ^гиркумчэ̄/*гиркумчэ̄$
1 ^а̄чина/*а̄чина$
coverage: 64 / 86 (~0.74418604651162790698) remaining unknown forms: 22
Bilingual Transducer Coverage
TOP UNKNOWN WORDS:
5 ^вэл/*вэл$
5 ^Илэтыкин/*Илэтыкин$
4 ^Ңи/*Ңи$
4 ^тэдет/*тэдет$
3 ^эвки/*эвки$
2 ^бинэ/*бинэ$
2 ^бимчэ/*бимчэ$
2 ^бидемэчин/*бидемэчин$
2 ^авадытыкин/*авадытыкин$
1 ^эңэсит/*эңэсит$
1 ^эсин/*эсин$
1 ^эрэ/*эрэ$
1 ^эмэмчэ/*эмэмчэ$
1 ^чина/*чина$
1 ^чивунду/*чивунду$
1 ^умунупкиттула/*умунупкиттула$
1 ^тэдэт/*тэдэт$
1 ^ты/*ты$
1 ^тури/*тури$
1 ^тартыки/*тартыки$
coverage: 20 / 99 (~0.20202020202020202020) remaining unknown forms: 79
Sentence Translation
| Original Sentence | Intended Translation | evn-eng-bilttrans | evn-eng |
|---|---|---|---|
| Илэтыкин индэ̄ви, мэ̄нңи илэчэврэви тэдет бимэчин. | Everyone has the right to life, liberty and the security of person. | ^Илэтыкин<n><sg><nom>/Everyone<prn><sg><nom>$ ^*индэ̄ви/*индэ̄ви$^,<cm>/,<cm>$ ^*мэ̄нңи/*мэ̄нңи$ ^*илэчэврэви/*илэчэврэви$ ^*тэдет/*тэдет$ ^*бимэчин/*бимэчин$^.<sent>/.<sent>$^.<sent>/.<sent>$ | “#Everyone *индэ̄ви, *мэ̄нңи *илэчэврэви *тэдет *бимэчин.” |
| Ңи-вэл кэсэгӣчивунду, са̄рича̄нинду эвки бидемэчин. | No one shall be subjected to torture or to cruel, inhuman or degrading treatment or punishment. | ^*Ңи/*Ңи$-^*вэл/*вэл$ ^*кэсэгӣчивунду/*кэсэгӣчивунду$^,<cm>/,<cm>$ ^*са̄рича̄нинду/*са̄рича̄нинду$ ^*эвки/*эвки$ ^*бидемэчин/*бидемэчин$^.<sent>/.<sent>$^.<sent>/.<sent>$ | *Ңи-*вэл *кэсэгӣчивунду, *са̄рича̄нинду *эвки *бидемэчин. |
| Илэтыкин, иду-вэл нуңан биденэ, тэдет бидемэчин | Everyone has the right to recognition everywhere as a person before the law. | ^Илэтыкин<n><sg><nom>/Everyone<prn><sg><nom>$^,<cm>/,<cm>$ ^иду<clit-val><adv>/@иду<clit-val><adv>$ ^*нуңан/*нуңан$ ^*биденэ/*биденэ$^,<cm>/,<cm>$ ^*тэдет/*тэдет$ ^*бидемэчин/*бидемэчин$^.<sent>/.<sent>$^.<sent>/.<sent>$ | #Everyone, @иду *нуңан *биденэ, *тэдет *бидемэчин. |
| Ңи-вэл дявамачин, турӣнмумачин, эрэ̄смэчин эсин о̄да. | No one shall be subjected to arbitrary arrest, detention or exile. | ^*Ңи/*Ңи$-^*вэл/*вэл$ ^*дявамачин/*дявамачин$^,<cm>/,<cm>$ ^*турӣнмумачин/*турӣнмумачин$^,<cm>/,<cm>$ ^*эрэ̄смэчин/*эрэ̄смэчин$ ^*эсин/*эсин$ ^*о̄да/*о̄да$^.<sent>/.<sent>$^.<sent>/.<sent>$ | *Ңи-*вэл *дявамачин, *турӣнмумачин, *эрэ̄смэчин *эсин *о̄да. |
| Илэтыкин авадытыкин государстваду бимчэ̄, гиркумчэ̄ | Everyone has the right to freedom of movement and residence within the borders of each State. | ^Илэтыкин<n><sg><nom>/Everyone<prn><sg><nom>$ ^авады̄тыкин<adj><sg><nom>/different<adj><sg><nom>$ ^*государстваду/*государстваду$ ^*бимчэ̄/*бимчэ̄$^,<cm>/,<cm>$ ^*гиркумчэ̄/*гиркумчэ̄$^.<sent>/.<sent>$ | #Everyone #different *государстваду *бимчэ̄, *гиркумчэ̄ |
| Илэтыкин авадытыкин государстводук сурумчэ̄, тартыки эмэмчэ̄-дэ̄. | Everyone has the right to leave any country, including his own, and to return to his country. | ^Илэтыкин<n><sg><nom>/Everyone<prn><sg><nom>$ ^авады̄тыкин<adj><sg><nom>/different<adj><sg><nom>$ ^*государстводук/*государстводук$ ^*сурумчэ̄/*сурумчэ̄$^,<cm>/,<cm>$ ^*тартыки/*тартыки$ ^*эмэмчэ̄/*эмэмчэ̄$-^*дэ̄/*дэ̄$^.<sent>/.<sent>$^.<sent>/.<sent>$ | #Everyone #different *государстводук *сурумчэ̄, *тартыки *эмэмчэ̄-*дэ̄. |
| Илэтыкин гражданствоват тэдет бимчэ̄. | Everyone has the right to a nationality. | ^Илэтыкин<n><sg><nom>/Everyone<prn><sg><nom>$ ^*гражданствоват/*гражданствоват$ ^*тэдет/*тэдет$ ^*бимчэ̄/*бимчэ̄$^.<sent>/.<sent>$^.<sent>/.<sent>$ | #Everyone *гражданствоват *тэдет *бимчэ̄. |
| Ңи-вэл илэдук идэгэен, авдуян тэдэт а̄чина эвки ты̄рэ. | No one shall be arbitrarily deprived of his property. | ^*Ңи/*Ңи$-^*вэл/*вэл$ ^*илэдук/*илэдук$ ^*идэгэен/*идэгэен$^,<cm>/,<cm>$ ^авду<n><sg><acc><ind><px3sg>/thing<n><sg><acc><ind><px3sg>/property<n><sg><acc><ind><px3sg>/utensils<n><sg><acc><ind><px3sg>/household<n><sg><acc><ind><px3sg>/belongings<n><sg><acc><ind><px3sg>$ ^*тэдэт/*тэдэт$ ^*а̄чина/*а̄чина$ ^*эвки/*эвки$ ^*ты̄рэ/*ты̄рэ$^.<sent>/.<sent>$^.<sent>/.<sent>$ | *Ңи-*вэл *илэдук *идэгэен, #thing *тэдэт *а̄чина *эвки *ты̄рэ. |
| Ңи-вэл авады-вал умунупкиттула эңэсит эвки ӣвувра. | No one may be compelled to belong to an association. | ^*Ңи/*Ңи$-^*вэл/*вэл$ ^*авады/*авады$-^*вал/*вал$ ^*умунупкиттула/*умунупкиттула$ ^*эңэсит/*эңэсит$ ^*эвки/*эвки$ ^*ӣвувра/*ӣвувра$^.<sent>/.<sent>$^.<sent>/.<sent>$ | *Ңи-*вэл *авады-*вал *умунупкиттула *эңэсит *эвки *ӣвувра. |
| Энин бинэ, куңака̄н бинэ тэдет бэлэнэ гэлэ̄дерэ. | Motherhood and childhood are entitled to special care and assistance. | ^*Энин/*Энин$ ^*бинэ/*бинэ$^,<cm>/,<cm>$ ^*куңака̄н/*куңака̄н$ ^*бинэ/*бинэ$ ^*тэдет/*тэдет$ ^*бэлэнэ/*бэлэнэ$ ^*гэлэ̄дерэ/*гэлэ̄дерэ$^.<sent>/.<sent>$^.<sent>/.<sent>$ | *Энин *бинэ, *куңака̄н *бинэ *тэдет *бэлэнэ *гэлэ̄дерэ. |
| Эр ӈӣ буруйдукин мунэвэ биргэ боконон? | What kind of work do you do? | ^*Эр/*Эр$ ^ӈӣ<prn><itg><sg><nom>/no one<prn><itg><sg><nom>$ ^*буруйдукин/*буруйдукин$ ^*мунэвэ/*мунэвэ$ ^*биргэ/*биргэ$ ^*боконон/*боконон$^?<sent>/?<sent>$^.<sent>/.<sent>$ | *Эр #no one *буруйдукин *мунэвэ *биргэ *боконон? |
| Сӣ ӈӣ? | Where do you come from? | ^*Сӣ/*Сӣ$ ^ӈӣ<prn><itg><sg><nom>/no one<prn><itg><sg><nom>$^?<sent>/?<sent>$^.<sent>/.<sent>$ | *Сӣ #no one? |
| Ӣдук эмэчс? | What is your country? | ^*Ӣдук/*Ӣдук$ ^*эмэчс/*эмэчс$^?<sent>/?<sent>$^.<sent>/.<sent>$ | *Ӣдук *эмэчс? |
| ма бугадук, ма тэгдук? | From what people are you? | ^*ма/*ма$ ^*бугадук/*бугадук$^,<cm>/,<cm>$ ^*ма/*ма$ ^*тэгдук/*тэгдук$^?<sent>/?<sent>$^.<sent>/.<sent>$ | *ма *бугадук, *ма *тэгдук? |
Note: Many of the words with stems entered into the bilingual dictionary are not translating despite being in both the monolingual and bilingual dictionaries (ie, based on our entries to apertium-evn.evn.lexc "Сӣ ӈӣ?" should be translating to "you where from?" or "you no-one" accounting for lack of disambiguation). We are unsure why although it seems to be an orthography issue with the transducer we pulled from apertium. We have been unable to resolve this problem at this time despite working with a TA for several hours. This has lead to artificially poor performance from our whole RBMT system pipeline.
Additions
Document which of the above options you completed on the pair's wiki page (in a section like "Additions"). You don't have to list the words or rules you added, but do list that you added n words or n transfer rules or the like.
Add a "polished RBMT system" tag to your repo.
EVN → ENG Final Evaluation
Monolingual Transducer
Updated precision and recall against the (updated) eval.test and eval.gold files (see Midterm overview#Evaluating your transducer),
Coverage over the large corpus,
The number of words in the large corpus,
The number of stems in the transducer.
Machine Translation
WER and PER over longer corpus.
The proportion of stems translated correctly in the longer corpus.
Trimmed coverage over longer and large corpora.
The number of tokens in longer and large corpora.
