On the Word Alignment from Neural Machine Translation

Xintong Li, Guanlin Li, Lemao Liu, Max Meng, Shuming Shi


Abstract
Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, this paper finds attention may almost fail to capture word alignment for some NMT models. This paper thereby proposes two methods to induce word alignment which are general and agnostic to specific NMT models. Experiments show that both methods induce much better word alignment than attention. This paper further visualizes the translation through the word alignment induced by NMT. In particular, it analyzes the effect of alignment errors on translation errors at word level and its quantitative analysis over many testing examples consistently demonstrate that alignment errors are likely to lead to translation errors measured by different metrics.
Anthology ID:
P19-1124
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1293–1303
Language:
URL:
https://aclanthology.org/P19-1124
DOI:
10.18653/v1/P19-1124
Bibkey:
Cite (ACL):
Xintong Li, Guanlin Li, Lemao Liu, Max Meng, and Shuming Shi. 2019. On the Word Alignment from Neural Machine Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1293–1303, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
On the Word Alignment from Neural Machine Translation (Li et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1124.pdf
Supplementary:
 P19-1124.Supplementary.pdf