This is not the latest version of this item. The latest version can be found here.
A game theoretic approach to class-wise selective rationalization
Name
NeurIPS-2019-a-game-theoretic-approach-to-class-wise-selective-rationalization-Paper.pdf
Description
Published version
Size
486.53 KB
Format
Adobe PDF
Checksum (MD5)
039f93328b8b38eab4ba0d2f6866851b
Author(s)
Chang, Shiyu
Zhang, Yang
Jaakkola, Tommi S
Journal
Advances in Neural Information Processing Systems
Citation
Chang, Shiyu, Zhang, Yang and Jaakkola, Tommi S. "A game theoretic approach to class-wise selective rationalization." Advances in Neural Information Processing Systems, 32.
Version
Final published version
Abstract
© 2019 Neural information processing systems foundation. All rights reserved. Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post-hoc for trained models or incorporated directly into the method itself (self-explaining). However, an overall selection does not properly capture the multi-faceted nature of useful rationales such as pros and cons for decisions. To this end, we propose a new game theoretic approach to class-dependent rationalization, where the method is specifically trained to highlight evidence supporting alternative conclusions. Each class involves three players set up competitively to find evidence for factual and counterfactual scenarios. We show theoretically in a simplified scenario how the game drives the solution towards meaningful class-dependent rationales. We evaluate the method in single- and multi-aspect sentiment classification tasks and demonstrate that the proposed method is able to identify both factual (justifying the ground truth label) and counterfactual (countering the ground truth label) rationales consistent with human rationalization. The code for our method is publicly available.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://papers.nips.cc/paper/2019/hash/5ad742cd15633b26fdce1b80f7b39f7c-Abstract.html
