Context-Aware Neural Machine Translation Learns Anaphora Resolution

Elena Voita, Pavel Serdyukov, Rico Sennrich, Ivan Titov


Abstract
Standard machine translation systems process sentences in isolation and hence ignore extra-sentential information, even though extended context can both prevent mistakes in ambiguous cases and improve translation coherence. We introduce a context-aware neural machine translation model designed in such way that the flow of information from the extended context to the translation model can be controlled and analyzed. We experiment with an English-Russian subtitles dataset, and observe that much of what is captured by our model deals with improving pronoun translation. We measure correspondences between induced attention distributions and coreference relations and observe that the model implicitly captures anaphora. It is consistent with gains for sentences where pronouns need to be gendered in translation. Beside improvements in anaphoric cases, the model also improves in overall BLEU, both over its context-agnostic version (+0.7) and over simple concatenation of the context and source sentences (+0.6).
Anthology ID:
P18-1117
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1264–1274
Language:
URL:
https://aclanthology.org/P18-1117
DOI:
10.18653/v1/P18-1117
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/P18-1117.pdf
Note:
 P18-1117.Notes.pdf
Video:
 https://vimeo.com/288152860
Presentation:
 P18-1117.Presentation.pdf
Data
OpenSubtitles