Diving Deep into Context-Aware Neural Machine Translation
Jingjing Huo, Christian Herold, Yingbo Gao, Leonard Dahlmann, Shahram Khadivi, Hermann Ney
Abstract
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various architectures and analyses, the effectiveness of different context-aware NMT models is not well explored yet. This paper analyzes the performance of document-level NMT models on four diverse domains with a varied amount of parallel document-level bilingual data. We conduct a comprehensive set of experiments to investigate the impact of document-level NMT. We find that there is no single best approach to document-level NMT, but rather that different architectures come out on top on different tasks. Looking at task-specific problems, such as pronoun resolution or headline translation, we find improvements in the context-aware systems, even in cases where the corpus-level metrics like BLEU show no significant improvement. We also show that document-level back-translation significantly helps to compensate for the lack of document-level bi-texts.- Anthology ID:
- 2020.wmt-1.71
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 604–616
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.71
- DOI:
- Cite (ACL):
- Jingjing Huo, Christian Herold, Yingbo Gao, Leonard Dahlmann, Shahram Khadivi, and Hermann Ney. 2020. Diving Deep into Context-Aware Neural Machine Translation. In Proceedings of the Fifth Conference on Machine Translation, pages 604–616, Online. Association for Computational Linguistics.
- Cite (Informal):
- Diving Deep into Context-Aware Neural Machine Translation (Huo et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.wmt-1.71.pdf
- Data
- OpenSubtitles