Neural Lattice Search for Domain Adaptation in Machine Translation

Huda Khayrallah, Gaurav Kumar, Kevin Duh, Matt Post, Philipp Koehn


Abstract
Domain adaptation is a major challenge for neural machine translation (NMT). Given unknown words or new domains, NMT systems tend to generate fluent translations at the expense of adequacy. We present a stack-based lattice search algorithm for NMT and show that constraining its search space with lattices generated by phrase-based machine translation (PBMT) improves robustness. We report consistent BLEU score gains across four diverse domain adaptation tasks involving medical, IT, Koran, or subtitles texts.
Anthology ID:
I17-2004
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
20–25
Language:
URL:
https://aclanthology.org/I17-2004
DOI:
Bibkey:
Cite (ACL):
Huda Khayrallah, Gaurav Kumar, Kevin Duh, Matt Post, and Philipp Koehn. 2017. Neural Lattice Search for Domain Adaptation in Machine Translation. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 20–25, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Neural Lattice Search for Domain Adaptation in Machine Translation (Khayrallah et al., IJCNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/I17-2004.pdf