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
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/D19-6503.pdf
- Code
- ducthanhtran/sockeye_document_context