Table 5: 
Tokenized BLEU scores on tst2013 for the low-resource IWSLT’15 English-Vietnamese translation task using bitext mined with our method. Added pairs are sorted by their score. Development scores on tst2012 in parentheses.
En-Vi
Luong and Manning (2015) 26.4 
Clark et al. (2018) 28.9 
Clark et al. (2018), with CVT 29.6 
Xu et al. (2019) 31.4 
Nguyen and Salazar (2019) 32.8 (28.8) 
 
+ top 100k mined pairs 33.2 (29.5) 
+ top 200k mined pairs 33.9 (29.8) 
+ top 300k mined pairs 34.0 (30.0) 
+ top 400k mined pairs 34.1 (29.9) 
En-Vi
Luong and Manning (2015) 26.4 
Clark et al. (2018) 28.9 
Clark et al. (2018), with CVT 29.6 
Xu et al. (2019) 31.4 
Nguyen and Salazar (2019) 32.8 (28.8) 
 
+ top 100k mined pairs 33.2 (29.5) 
+ top 200k mined pairs 33.9 (29.8) 
+ top 300k mined pairs 34.0 (30.0) 
+ top 400k mined pairs 34.1 (29.9) 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept