Neural rationale models are popular for interpretable predictions of NLP tasks. In these, a selector extracts segments of the input text, called rationales, and passes these segments to a classifier for prediction. Since the rationale is the only information accessible to the classifier, it is plausibly defined as the explanation. Is such a characterization unconditionally correct? In this paper, we argue to the contrary, with both philosophical perspectives and empirical evidence suggesting that rationale models are, perhaps, less rational and interpretable than expected. We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved. The code can be found at https://github.com/yimingz89/Neural-Rationale-Analysis.
Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
University of California, Santa Cruz(加州大学圣克鲁兹分校);Allen Institute for AI(艾伦人工智能研究所);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);University of Maryland, College Park(马里兰大学学院公园分校)
A Framework for Rationale Extraction for Deep QA models
Robert Bosch Centre for Data Science and AI (RBC-DSAI)(罗伯特·博世数据科学与人工智能中心(RBC-DSAI));Indian Institute of Technology Madras(印度理工学院马德拉斯分校);Google Research(谷歌研究院)
Using Interpretation Methods for Model Enhancement
School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程技术研究中心)
Rationalizing Medical Relation Prediction from Corpus-level Statistics
The Ohio State University(俄亥俄州立大学);The Ohio State University Wexner Medical Center(俄亥俄州立大学韦克斯纳医学中心);Nationwide Children’s Hospital(全国儿童医院);Abigail Wexner Research Institute at Nationwide Children’s Hospital(全国儿童医院阿比盖尔·韦克斯纳研究所)
Rationalizing Predictions by Adversarial Information Calibration
Beihang University(北京航空航天大学);University of Oxford(牛津大学);University College London(伦敦大学学院);TU Wien(维也纳工业大学);Alan Turing Institute(艾伦·图灵研究所);Zhongguancun Laboratory(中关村实验室)