Difference between revisions of "Wamesa and Tongan"

From LING073
Jump to: navigation, search
(wad → ton evaluation)
Line 25: Line 25:
 
==Final Evaluation==
 
==Final Evaluation==
 
===Wamesa Transducer===
 
===Wamesa Transducer===
There are about 110 stems in the transducer, and about 160 in the translation system. Precision and recall for the <code>wad.annotated.basic.txt</code> corpus are both 100%. There are words in the <code>wad.large.txt</code> corpus, and the coverage over it is TODO.
+
There are about 110 stems in the transducer, and about 160 in the translation system. Precision and recall for the <code>wad.annotated.basic.txt</code> corpus are both 100%. There are 940 words in the <code>wad.large.txt</code> corpus, and the coverage over it is 26.17%.
  
 
===Tongan Transducer===
 
===Tongan Transducer===
  
 
===wad → ton evaluation===
 
===wad → ton evaluation===
WER and PER over the <code>wad.longer.txt</code> corpus were both 100%
+
WER and PER over the <code>wad.longer.txt</code> corpus were both 100%. The coverage over the <code>large</code> corpus was 26.17%, and was the same for the <code>longer</code> corpus.<br/>
 
There are 934 tokens in the <code>longer</code> corpus and 940 in the <code>large</code> corpus.
 
There are 934 tokens in the <code>longer</code> corpus and 940 in the <code>large</code> corpus.
  
Line 43: Line 43:
 
[https://github.swarthmore.edu/mcostag1/ling073-ton-wad.git ton→wad translator]<br/>
 
[https://github.swarthmore.edu/mcostag1/ling073-ton-wad.git ton→wad translator]<br/>
 
[https://github.swarthmore.edu/twarner2/ling073-wad-ton.git wad→ton translator]<br/>
 
[https://github.swarthmore.edu/twarner2/ling073-wad-ton.git wad→ton translator]<br/>
 +
[https://github.swarthmore.edu/mcostag1/ling073-ton-wad Bidirectional Wamesa/Tongan Translator]<br/>
  
  

Revision as of 20:32, 27 April 2017

This page is a resource for machine translation between Wamesa and Tongan.

Initial Evaluation

wad → ton evaluation

On the tests file, 77.47% of the words translate correctly, and the unknown word rate is 28.57%. The WER and PER are both 71.43% when *'d words are removed, and 100% when not removing *'s.

ton → wad evaluation

Percentage of unknown words in ton.sentences.txt (bilingual corpus): 7%

Percentage of stems translated correctly: 93%

Percentage of unknown words in test file: 0%

Results when removing unknown word marks (stars) | WER: 100% PER: 100% Number of position-independent correct words: 1

Results when unknown word marks (stars) not removed | WER: 100% PER: 100%

  • There is still one bug that we are trying to fix. siʻaku is being translated to #<poss>, but it should translate to nothing as there is no equivalent in Wamesa. The percentages above are when the incorrect #<poss> is taken out of the ton-wad.tests.txt file. Otherwise, the percentage increases to 114.29%.

Final Evaluation

Wamesa Transducer

There are about 110 stems in the transducer, and about 160 in the translation system. Precision and recall for the wad.annotated.basic.txt corpus are both 100%. There are 940 words in the wad.large.txt corpus, and the coverage over it is 26.17%.

Tongan Transducer

wad → ton evaluation

WER and PER over the wad.longer.txt corpus were both 100%. The coverage over the large corpus was 26.17%, and was the same for the longer corpus.
There are 934 tokens in the longer corpus and 940 in the large corpus.

ton → wad evaluation

Documentation

Contrastive Grammar
Lexical Selection
Structural Transfer

Developed Resources

ton→wad translator
wad→ton translator
Bidirectional Wamesa/Tongan Translator