KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference

Qianglong Chen, Feng Ji, Xiangji Zeng, Feng-Lin Li, Ji Zhang, Haiqing Chen, Yin Zhang


Abstract
In order to better understand the reason behind model behaviors (i.e., making predictions), most recent works have exploited generative models to provide complementary explanations. However, existing approaches in NLP mainly focus on “WHY A” rather than contrastive “WHY A NOT B”, which is shown to be able to better distinguish confusing candidates and improve data efficiency in other research fields.In this paper, we focus on generating contrastive explanations with counterfactual examples in NLI and propose a novel Knowledge-Aware Contrastive Explanation generation framework (KACE).Specifically, we first identify rationales (i.e., key phrases) from input sentences, and use them as key perturbations for generating counterfactual examples. After obtaining qualified counterfactual examples, we take them along with original examples and external knowledge as input, and employ a knowledge-aware generative pre-trained language model to generate contrastive explanations. Experimental results show that contrastive explanations are beneficial to fit the scenarios by clarifying the difference between the predicted answer and other possible wrong ones. Moreover, we train an NLI model enhanced with contrastive explanations and achieves an accuracy of 91.9% on SNLI, gaining improvements of 5.7% against ETPA (“Explain-Then-Predict-Attention”) and 0.6% against NILE (“WHY A”).
Anthology ID:
2021.acl-long.196
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
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2516–2527
Language:
URL:
https://aclanthology.org/2021.acl-long.196
DOI:
10.18653/v1/2021.acl-long.196
Bibkey:
Cite (ACL):
Qianglong Chen, Feng Ji, Xiangji Zeng, Feng-Lin Li, Ji Zhang, Haiqing Chen, and Yin Zhang. 2021. KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference. 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 2516–2527, Online. Association for Computational Linguistics.
Cite (Informal):
KACE: Generating Knowledge Aware Contrastive Explanations for Natural Language Inference (Chen et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.196.pdf
Video:
 https://aclanthology.org/2021.acl-long.196.mp4
Code
 ai4nlp/kace
Data
IMDb Movie ReviewsSNLIe-SNLI