When and Why is Document-level Context Useful in Neural Machine Translation?

Yunsu Kim, Duc Thanh Tran, Hermann Ney


Abstract
Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its improvement with only a few selected examples or targeted test sets. We extensively quantify the causes of improvements by a document-level model in general test sets, clarifying the limit of the usefulness of document-level context in NMT. We show that most of the improvements are not interpretable as utilizing the context. We also show that a minimal encoding is sufficient for the context modeling and very long context is not helpful for NMT.
Anthology ID:
D19-6503
Volume:
Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venue:
DiscoMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
24–34
Language:
URL:
https://aclanthology.org/D19-6503
DOI:
10.18653/v1/D19-6503
Bibkey:
Cite (ACL):
Yunsu Kim, Duc Thanh Tran, and Hermann Ney. 2019. When and Why is Document-level Context Useful in Neural Machine Translation?. In Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019), pages 24–34, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
When and Why is Document-level Context Useful in Neural Machine Translation? (Kim et al., DiscoMT 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-6503.pdf
Attachment:
 D19-6503.Attachment.pdf
Code
 ducthanhtran/sockeye_document_context