Six Challenges for Neural Machine Translation

Add code
Jun 12, 2017
Philipp Koehn, Rebecca Knowles
Figure 1 for Six Challenges for Neural Machine Translation
Figure 2 for Six Challenges for Neural Machine Translation
Figure 3 for Six Challenges for Neural Machine Translation
Figure 4 for Six Challenges for Neural Machine Translation

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search. We show both deficiencies and improvements over the quality of phrase-based statistical machine translation.

* 12 pages; First Workshop on Neural Machine Translation, 2017  
View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon