Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation

Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, Changliang Li


Abstract
In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigate multi-encoder approaches in document-level neural machine translation (NMT). Surprisingly, we find that the context encoder does not only encode the surrounding sentences but also behaves as a noise generator. This makes us rethink the real benefits of multi-encoder in context-aware translation - some of the improvements come from robust training. We compare several methods that introduce noise and/or well-tuned dropout setup into the training of these encoders. Experimental results show that noisy training plays an important role in multi-encoder-based NMT, especially when the training data is small. Also, we establish a new state-of-the-art on IWSLT Fr-En task by careful use of noise generation and dropout methods.
Anthology ID:
2020.acl-main.322
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3512–3518
Language:
URL:
https://aclanthology.org/2020.acl-main.322
DOI:
10.18653/v1/2020.acl-main.322
Bibkey:
Cite (ACL):
Bei Li, Hui Liu, Ziyang Wang, Yufan Jiang, Tong Xiao, Jingbo Zhu, Tongran Liu, and Changliang Li. 2020. Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3512–3518, Online. Association for Computational Linguistics.
Cite (Informal):
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (Li et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.acl-main.322.pdf
Video:
 http://slideslive.com/38929005
Code
 libeineu/Context-Aware