Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models

Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, Masaaki Nagata


Abstract
Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor. Conventionally, many studies have used an attention matrix to interpret how Encoder-Decoder-based models translate a given source sentence to the corresponding target sentence. However, recent studies have empirically revealed that an attention matrix is not optimal for token-wise translation analyses. We propose a method that explicitly models the token-wise alignment between the source and target sequences to provide a better analysis. Experiments show that our method can acquire token-wise alignments that are superior to those of an attention mechanism.
Anthology ID:
W18-5410
Volume:
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Month:
November
Year:
2018
Address:
Brussels, Belgium
Editors:
Tal Linzen, Grzegorz Chrupała, Afra Alishahi
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
74–81
Language:
URL:
https://aclanthology.org/W18-5410
DOI:
10.18653/v1/W18-5410
Bibkey:
Cite (ACL):
Shun Kiyono, Sho Takase, Jun Suzuki, Naoaki Okazaki, Kentaro Inui, and Masaaki Nagata. 2018. Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 74–81, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models (Kiyono et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5410.pdf