Saliency Learning: Teaching the Model Where to Pay Attention

Reza Ghaeini, Xiaoli Fern, Hamed Shahbazi, Prasad Tadepalli


Abstract
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches to provide insights toward the model’s behaviour and predictions, which are helpful for assessing the reliability of the model’s predictions. However, such methods do not improve the model’s reliability. In this paper, we aim to teach the model to make the right prediction for the right reason by providing explanation training and ensuring the alignment of the model’s explanation with the ground truth explanation. Our experimental results on multiple tasks and datasets demonstrate the effectiveness of the proposed method, which produces more reliable predictions while delivering better results compared to traditionally trained models.
Anthology ID:
N19-1404
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4016–4025
Language:
URL:
https://aclanthology.org/N19-1404
DOI:
10.18653/v1/N19-1404
Bibkey:
Cite (ACL):
Reza Ghaeini, Xiaoli Fern, Hamed Shahbazi, and Prasad Tadepalli. 2019. Saliency Learning: Teaching the Model Where to Pay Attention. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4016–4025, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Saliency Learning: Teaching the Model Where to Pay Attention (Ghaeini et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1404.pdf