Importance of Self-Attention for Sentiment Analysis

Gaël Letarte, Frédérik Paradis, Philippe Giguère, François Laviolette


Abstract
Despite their superior performance, deep learning models often lack interpretability. In this paper, we explore the modeling of insightful relations between words, in order to understand and enhance predictions. To this effect, we propose the Self-Attention Network (SANet), a flexible and interpretable architecture for text classification. Experiments indicate that gains obtained by self-attention is task-dependent. For instance, experiments on sentiment analysis tasks showed an improvement of around 2% when using self-attention compared to a baseline without attention, while topic classification showed no gain. Interpretability brought forward by our architecture highlighted the importance of neighboring word interactions to extract sentiment.
Anthology ID:
W18-5429
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:
267–275
Language:
URL:
https://aclanthology.org/W18-5429
DOI:
10.18653/v1/W18-5429
Bibkey:
Cite (ACL):
Gaël Letarte, Frédérik Paradis, Philippe Giguère, and François Laviolette. 2018. Importance of Self-Attention for Sentiment Analysis. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 267–275, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Importance of Self-Attention for Sentiment Analysis (Letarte et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-5429.pdf
Data
Yahoo! AnswersYelp Review Polarity