CASIA OpenIR  > 复杂系统认知与决策实验室
Alignment Rationale for Natural Language Inference
Zhongtao Jiang1,2; Yuanzhe Zhang1,2; Zhao Yang1,2; Jun Zhao1,2; Kang Liu1,2
Conference NameProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
Conference Date2021-8-1
Conference PlaceOnline

Deep learning models have achieved great success on the task of Natural Language Inference (NLI), though only a few attempts try to explain their behaviors. Existing explanation methods usually pick prominent features such as words or phrases from the input text. However, for NLI, alignments among words or phrases are more enlightening clues to explain the model. To this end, this paper presents AREC, a post-hoc approach to generate alignment rationale explanations for co-attention based models in NLI. The explanation is based on feature selection, which keeps few but sufficient alignments while maintaining the same prediction of the target model. Experimental results show that our method is more faithful and human-readable compared with many existing approaches. We further study and re-evaluate three typical models through our explanation beyond accuracy, and propose a simple method that greatly improves the model robustness.

Sub direction classification自然语言处理
planning direction of the national heavy laboratory语音语言处理
Paper associated data
Document Type会议论文
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Zhongtao Jiang,Yuanzhe Zhang,Zhao Yang,et al. Alignment Rationale for Natural Language Inference[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
Alignment Rationale (1280KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhongtao Jiang]'s Articles
[Yuanzhe Zhang]'s Articles
[Zhao Yang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhongtao Jiang]'s Articles
[Yuanzhe Zhang]'s Articles
[Zhao Yang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhongtao Jiang]'s Articles
[Yuanzhe Zhang]'s Articles
[Zhao Yang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Alignment Rationale for Natural Language Inference.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.