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
Editors:
Thang Luong, Alexandra Birch, Graham Neubig, Andrew Finch
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
28–39
Language:
URL:
https://aclanthology.org/W17-3204
DOI:
10.18653/v1/W17-3204
Bibkey:
Cite (ACL):
Philipp Koehn and Rebecca Knowles. 2017. Six Challenges for Neural Machine Translation. In Proceedings of the First Workshop on Neural Machine Translation, pages 28–39, Vancouver. Association for Computational Linguistics.
Cite (Informal):
Six Challenges for Neural Machine Translation (Koehn & Knowles, NGT 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-3204.pdf