Evenki and English - Revision history

Ptrifon1 at 16:51, 11 May 2023

2023-05-11T16:51:10Z

2023-05-11T16:45:13Z

‎EVN → ENG Final Evaluation

2023-05-11T15:19:56Z

‎Additions

2023-05-11T14:56:11Z

‎Additions

2023-05-11T13:55:05Z

‎Additions

2023-05-11T13:08:48Z

‎Sentence Translation

2023-05-11T13:08:00Z

‎Sentence Translation

2023-05-10T21:31:13Z

‎Developed Resources

2023-05-10T18:37:41Z

‎Sentence Translation

2023-05-10T18:36:02Z

‎Sentence Translation

@@ Line 210: / Line 210: @@
         тар
   Translation time: 0.04945206642150879 seconds
 [[Category:Sp23_TranslationPairs]]

@@ Line 117: / Line 117: @@
 '''Monolingual Transducer'''
-        Updated precision and recall against the (updated) eval.test and eval.gold files (see Midterm overview#Evaluating your transducer),
+ Note: We used a preexisting transducer for evenki on apertium and did not produce the transducer we used ourselves.
-        Coverage over the large corpus,
-        The number of words in the large corpus,
+Updated precision and recall against the (updated) eval.test and eval.gold files:
-        The number of stems in the transducer.
+ We tried to run precision and recall against the bible corpus and received the following error:
 '''Machine Translation'''
-        WER and PER over longer corpus.
-        The proportion of stems translated correctly in the longer corpus.
+WER and PER over longer corpus:
-        Trimmed coverage over longer and large corpora.
+ -------------------------------------------------------
-        The number of tokens in longer and large corpora.
+ Number of words in reference: 141
 [[Category:Sp23_TranslationPairs]]

@@ Line 113: / Line 113: @@
 === Additions ===
 * Added 5 New Lexical Selection rules
 === EVN → ENG Final Evaluation ===

@@ Line 112: / Line 112: @@
 === Additions ===
-* Added 2 New Lexical Selection rules
+* Added 5 New Lexical Selection rules
-* Added 2 New Transfer Rules
 Add a "polished RBMT system" tag to your repo.

@@ Line 112: / Line 112: @@
 === 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.
+* Added 2 New Lexical Selection rules
 Add a "polished RBMT system" tag to your repo.

@@ 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 ===

@@ Line 12: / Line 12: @@
 [https://wikis.swarthmore.edu/ling073/Evenki_and_English/Contrastive_Grammar Contrastive Grammar]
 ===EVN → ENG Initial Evaluation===
 '''Monolingual Transducer Coverage'''

@@ Line 106: / Line 106: @@
 |}
-Note: Many of the words with stems entered into the bilingual dictionary are not translating. We are unsure why and have been unable to resolve this problem at this time.
+Note: Many of the words with stems entered into the bilingual dictionary are not translating (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 and have been unable to resolve this problem at this time.
 === Additions ===