Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling

David Harbecke, Christoph Alt


Abstract
Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model’s decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete distribution of data in NLP. Thus, we propose OLM: a novel explanation method that combines occlusion and language models to sample valid and syntactically correct replacements with high likelihood, given the context of the original input. We lay out a theoretical foundation that alleviates these weaknesses of other explanation methods in NLP and provide results that underline the importance of considering data likelihood in occlusion-based explanation.
Anthology ID:
2020.acl-srw.16
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
111–117
Language:
URL:
https://aclanthology.org/2020.acl-srw.16
DOI:
10.18653/v1/2020.acl-srw.16
Bibkey:
Cite (ACL):
David Harbecke and Christoph Alt. 2020. Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 111–117, Online. Association for Computational Linguistics.
Cite (Informal):
Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling (Harbecke & Alt, ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-srw.16.pdf
Video:
 http://slideslive.com/38928653
Code
 DFKI-NLP/OLM
Data
CoLAMultiNLISST