NILE : Natural Language Inference with Faithful Natural Language Explanations

Sawan Kumar, Partha Talukdar


Abstract
The recent growth in the popularity and success of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of the predicted labels. Such generated natural language (NL) explanations are expected to be faithful, i.e., they should correlate well with the model’s internal decision making. In this work, we focus on the task of natural language inference (NLI) and address the following question: can we build NLI systems which produce labels with high accuracy, while also generating faithful explanations of its decisions? We propose Natural-language Inference over Label-specific Explanations (NILE), a novel NLI method which utilizes auto-generated label-specific NL explanations to produce labels along with its faithful explanation. We demonstrate NILE’s effectiveness over previously reported methods through automated and human evaluation of the produced labels and explanations. Our evaluation of NILE also supports the claim that accurate systems capable of providing testable explanations of their decisions can be designed. We discuss the faithfulness of NILE’s explanations in terms of sensitivity of the decisions to the corresponding explanations. We argue that explicit evaluation of faithfulness, in addition to label and explanation accuracy, is an important step in evaluating model’s explanations. Further, we demonstrate that task-specific probes are necessary to establish such sensitivity.
Anthology ID:
2020.acl-main.771
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8730–8742
Language:
URL:
https://aclanthology.org/2020.acl-main.771
DOI:
10.18653/v1/2020.acl-main.771
Bibkey:
Cite (ACL):
Sawan Kumar and Partha Talukdar. 2020. NILE : Natural Language Inference with Faithful Natural Language Explanations. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8730–8742, Online. Association for Computational Linguistics.
Cite (Informal):
NILE : Natural Language Inference with Faithful Natural Language Explanations (Kumar & Talukdar, ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.771.pdf
Video:
 http://slideslive.com/38929362
Code
 SawanKumar28/nile
Data
MultiNLISNLIe-SNLI