Abstract
Recently a number of approaches have been proposed to improve translation performance for document-level neural machine translation (NMT). However, few are focusing on the subject of lexical translation consistency. In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT. This is done by first obtaining a word link for each source word in a document, which tells the positions where the source word appears. Then we encourage the translation of those words within a link to be consistent in two ways. On the one hand, when encoding sentences within a document we properly share context information of those words. On the other hand, we propose an auxiliary loss function to better constrain that their translation should be consistent. Experimental results on Chinese↔English and English→French translation tasks show that our approach not only achieves state-of-the-art performance in BLEU scores, but also greatly improves lexical consistency in translation.- Anthology ID:
- 2021.emnlp-main.262
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3265–3277
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.262
- DOI:
- 10.18653/v1/2021.emnlp-main.262
- Cite (ACL):
- Xinglin Lyu, Junhui Li, Zhengxian Gong, and Min Zhang. 2021. Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3265–3277, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation (Lyu et al., EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.emnlp-main.262.pdf