Understanding Attention for Text Classification

Xiaobing Sun, Wei Lu


Abstract
Attention has been proven successful in many natural language processing (NLP) tasks. Recently, many researchers started to investigate the interpretability of attention on NLP tasks. Many existing approaches focused on examining whether the local attention weights could reflect the importance of input representations. In this work, we present a study on understanding the internal mechanism of attention by looking into the gradient update process, checking its behavior when approaching a local minimum during training. We propose to analyze for each word token the following two quantities: its polarity score and its attention score, where the latter is a global assessment on the token’s significance. We discuss conditions under which the attention mechanism may become more (or less) interpretable, and show how the interplay between the two quantities can contribute towards model performance.
Anthology ID:
2020.acl-main.312
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3418–3428
Language:
URL:
https://aclanthology.org/2020.acl-main.312
DOI:
10.18653/v1/2020.acl-main.312
Bibkey:
Cite (ACL):
Xiaobing Sun and Wei Lu. 2020. Understanding Attention for Text Classification. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3418–3428, Online. Association for Computational Linguistics.
Cite (Informal):
Understanding Attention for Text Classification (Sun & Lu, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.312.pdf
Video:
 http://slideslive.com/38929360