Difference between revisions of "Wamesa and Tongan"
(→Documentation) |
(→ton → wad evaluation) |
||
Line 5: | Line 5: | ||
===ton → wad evaluation=== | ===ton → wad evaluation=== | ||
− | Percentage of unknown words: 0% | + | |
+ | |||
+ | Percentage of unknown words in ton.sentences.txt (bilingual corpus): 7% | ||
+ | Percentage of unknown words in test file: 0% | ||
Results when removing unknown word marks (stars) | | Results when removing unknown word marks (stars) | |
Revision as of 12:14, 26 March 2017
This page is a resource for machine translation between Wamesa and Tongan.
Contents
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 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%.
Lexical Selection
wad → ton
In Wamesa, the 3rd person plural is indicated by a morpheme, but in Tongan, it can appear as a few different words.
- (wad) se- → ou (ton)
- (wad) se- → kinautolu (ton)
Wamesa only has one word for sick, while Tongan has a few.
- (wad) pota → puke (ton)
- (wad) pota → ʻa (ton)
ton → wad
Tongan only has one word for to swim, while Wamesa has a few.
- (ton) kakau → as (wad)
- (ton) kakau → kubira (wad)
Tongan has one word for ocean, while Wamesa has a couple.
- (ton) moana → sasi (wad)
- (ton) moana → rawanam (wad)