Abstract
Attention in neural machine translation provides the possibility to encode relevant parts of the source sentence at each translation step. As a result, attention is considered to be an alignment model as well. However, there is no work that specifically studies attention and provides analysis of what is being learned by attention models. Thus, the question still remains that how attention is similar or different from the traditional alignment. In this paper, we provide detailed analysis of attention and compare it to traditional alignment. We answer the question of whether attention is only capable of modelling translational equivalent or it captures more information. We show that attention is different from alignment in some cases and is capturing useful information other than alignments.- Anthology ID:
- I17-1004
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 30–39
- Language:
- URL:
- https://aclanthology.org/I17-1004
- DOI:
- Cite (ACL):
- Hamidreza Ghader and Christof Monz. 2017. What does Attention in Neural Machine Translation Pay Attention to?. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 30–39, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- What does Attention in Neural Machine Translation Pay Attention to? (Ghader & Monz, IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/I17-1004.pdf