Counterfactual Explanations for Natural Language Interfaces
George Tolkachev, Stephen Mell, Stephan Zdancewic, Osbert Bastani
Abstract
A key challenge facing natural language interfaces is enabling users to understand the capabilities of the underlying system. We propose a novel approach for generating explanations of a natural language interface based on semantic parsing. We focus on counterfactual explanations, which are post-hoc explanations that describe to the user how they could have minimally modified their utterance to achieve their desired goal. In particular, the user provides an utterance along with a demonstration of their desired goal; then, our algorithm synthesizes a paraphrase of their utterance that is guaranteed to achieve their goal. In two user studies, we demonstrate that our approach substantially improves user performance, and that it generates explanations that more closely match the user’s intent compared to two ablations.- Anthology ID:
- 2022.acl-short.14
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 113–118
- Language:
- URL:
- https://aclanthology.org/2022.acl-short.14
- DOI:
- 10.18653/v1/2022.acl-short.14
- Cite (ACL):
- George Tolkachev, Stephen Mell, Stephan Zdancewic, and Osbert Bastani. 2022. Counterfactual Explanations for Natural Language Interfaces. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 113–118, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Counterfactual Explanations for Natural Language Interfaces (Tolkachev et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2022.acl-short.14.pdf
- Code
- georgeto20/counterfactual_explanations