Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness?

293Citations
Citations of this article
348Readers
Mendeley users who have this article in their library.

Abstract

With the growing popularity of deep-learning based NLP models, comes a need for interpretable systems. But what is interpretability, and what constitutes a high-quality interpretation? In this opinion piece we reflect on the current state of interpretability evaluation research. We call for more clearly differentiating between different desired criteria an interpretation should satisfy, and focus on the faithfulness criteria. We survey the literature with respect to faithfulness evaluation, and arrange the current approaches around three assumptions, providing an explicit form to how faithfulness is “defined” by the community. We provide concrete guidelines on how evaluation of interpretation methods should and should not be conducted. Finally, we claim that the current binary definition for faithfulness sets a potentially unrealistic bar for being considered faithful. We call for discarding the binary notion of faithfulness in favor of a more graded one, which we believe will be of greater practical utility.

Cite

CITATION STYLE

APA

Jacovi, A., & Goldberg, Y. (2020). Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? In Proceedings of the Annual Meeting of the Association for Computational Linguistics (pp. 4198–4205). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.acl-main.386

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free