Exploring Distantly-Labeled Rationales in Neural Network Models

Quzhe Huang, Shengqi Zhu, Yansong Feng, Dongyan Zhao


Abstract
Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models’ focus to distantly-labeled rationale words entirely and equally, while ignoring the potential important non-rationale words and not distinguishing the importance of different rationale words. In this paper, we propose two novel auxiliary loss functions to make better use of distantly-labeled rationales, which encourage models to maintain their focus on important words beyond labeled rationales (PINs) and alleviate redundant training on non-helpful rationales (NoIRs). Experiments on two representative classification tasks show that our proposed methods can push a classification model to effectively learn crucial clues from non-perfect rationales while maintaining the ability to spread its focus to other unlabeled important words, thus significantly outperform existing methods.
Anthology ID:
2021.acl-long.433
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5571–5582
Language:
URL:
https://aclanthology.org/2021.acl-long.433
DOI:
10.18653/v1/2021.acl-long.433
Bibkey:
Cite (ACL):
Quzhe Huang, Shengqi Zhu, Yansong Feng, and Dongyan Zhao. 2021. Exploring Distantly-Labeled Rationales in Neural Network Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 5571–5582, Online. Association for Computational Linguistics.
Cite (Informal):
Exploring Distantly-Labeled Rationales in Neural Network Models (Huang et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.433.pdf
Video:
 https://aclanthology.org/2021.acl-long.433.mp4
Data
SST