Six Challenges for Neural Machine Translation

Philipp Koehn, Rebecca Knowles


Abstract
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.
Anthology ID:
W17-3204
Volume:
Proceedings of the First Workshop on Neural Machine Translation
Month:
August
Year:
2017
Address:
Vancouver
Venues:
NGT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
28–39
URL:
https://www.aclweb.org/anthology/W17-3204
DOI:
10.18653/v1/W17-3204
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/W17-3204.pdf