Encoders Help You Disambiguate Word Senses in Neural Machine Translation

Gongbo Tang, Rico Sennrich, Joakim Nivre


Abstract
Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of NMT encoders and decoders to disambiguate word senses by evaluating hidden states and investigating the distributions of self-attention. We train a classifier to predict whether a translation is correct given the representation of an ambiguous noun. We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequately encode relevant information for disambiguation into hidden states. In contrast to encoders, the effect of decoder is different in models with different architectures. Moreover, the attention weights and attention entropy show that self-attention can detect ambiguous nouns and distribute more attention to the context.
Anthology ID:
D19-1149
Erratum e1:
D19-1149e1
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
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1429–1435
Language:
URL:
https://aclanthology.org/D19-1149
DOI:
10.18653/v1/D19-1149
Bibkey:
Cite (ACL):
Gongbo Tang, Rico Sennrich, and Joakim Nivre. 2019. Encoders Help You Disambiguate Word Senses in Neural Machine Translation. 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 1429–1435, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Encoders Help You Disambiguate Word Senses in Neural Machine Translation (Tang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1149.pdf
Attachment:
 D19-1149.Attachment.zip