Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis

Jialong Tang, Ziyao Lu, Jinsong Su, Yubin Ge, Linfeng Song, Le Sun, Jiebo Luo


Abstract
In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. However, such a mechanism tends to excessively focus on a few frequent words with sentiment polarities, while ignoring infrequent ones. In this paper, we propose a progressive self-supervised attention learning approach for neural ASC models, which automatically mines useful attention supervision information from a training corpus to refine attention mechanisms. Specifically, we iteratively conduct sentiment predictions on all training instances. Particularly, at each iteration, the context word with the maximum attention weight is extracted as the one with active/misleading influence on the correct/incorrect prediction of every instance, and then the word itself is masked for subsequent iterations. Finally, we augment the conventional training objective with a regularization term, which enables ASC models to continue equally focusing on the extracted active context words while decreasing weights of those misleading ones. Experimental results on multiple datasets show that our proposed approach yields better attention mechanisms, leading to substantial improvements over the two state-of-the-art neural ASC models. Source code and trained models are available at https://github.com/DeepLearnXMU/PSSAttention.
Anthology ID:
P19-1053
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
557–566
Language:
URL:
https://aclanthology.org/P19-1053
DOI:
10.18653/v1/P19-1053
Bibkey:
Cite (ACL):
Jialong Tang, Ziyao Lu, Jinsong Su, Yubin Ge, Linfeng Song, Le Sun, and Jiebo Luo. 2019. Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 557–566, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis (Tang et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/P19-1053.pdf
Code
 DeepLearnXMU/PSSAttention
Data
SemEval 2014 Task 4 Sub Task 2