Header

UZH-Logo

Maintenance Infos

Context-Aware Neural Machine Translation Learns Anaphora Resolution


Voita, Elena; Serdyukov, Pavel; Sennrich, Rico; Titov, Ivan (2018). Context-Aware Neural Machine Translation Learns Anaphora Resolution. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, 15 July 2018 - 20 July 2018, 1264-1274.

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).

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).

Statistics

Downloads

6 downloads since deposited on 10 Apr 2019
6 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Language:English
Event End Date:20 July 2018
Deposited On:10 Apr 2019 12:41
Last Modified:11 Apr 2019 01:11
Publisher:Association for Computational Linguistics
OA Status:Green
Free access at:Official URL. An embargo period may apply.
Official URL:http://aclweb.org/anthology/P18-1117
Project Information:
  • : FunderSNSF
  • : Grant ID105212_169888
  • : Project TitleRich Context in Neural Machine Translation

Download

Download PDF  'Context-Aware Neural Machine Translation Learns Anaphora Resolution'.
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 1MB
Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)