Towards Understanding Neural Machine Translation with Word Importance

Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael Lyu, Shuming Shi


Abstract
Although neural machine translation (NMT) has advanced the state-of-the-art on various language pairs, the interpretability of NMT remains unsatisfactory. In this work, we propose to address this gap by focusing on understanding the input-output behavior of NMT models. Specifically, we measure the word importance by attributing the NMT output to every input word through a gradient-based method. We validate the approach on a couple of perturbation operations, language pairs, and model architectures, demonstrating its superiority on identifying input words with higher influence on translation performance. Encouragingly, the calculated importance can serve as indicators of input words that are under-translated by NMT models. Furthermore, our analysis reveals that words of certain syntactic categories have higher importance while the categories vary across language pairs, which can inspire better design principles of NMT architectures for multi-lingual translation.
Anthology ID:
D19-1088
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
953–962
Language:
URL:
https://aclanthology.org/D19-1088
DOI:
10.18653/v1/D19-1088
Bibkey:
Cite (ACL):
Shilin He, Zhaopeng Tu, Xing Wang, Longyue Wang, Michael Lyu, and Shuming Shi. 2019. Towards Understanding Neural Machine Translation with Word Importance. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 953–962, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Towards Understanding Neural Machine Translation with Word Importance (He et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1088.pdf
Attachment:
 D19-1088.Attachment.pdf