Counterfactual Explanations for Natural Language Interfaces

Citations Over TimeTop 23% of 2022 papers

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. 1

Related Papers

• → Counterfactual Explanations for Natural Language Interfaces(2022)6 cited
• → Testing Paraphrase Models on Recognising Sentence Pairs at Different Degrees of Semantic Overlap(2023)1 cited
• → Domain-Agnostic Context-Aware Framework for Natural Language Interface in a Task-Based Environment(2021)2 cited
• → Research on Chinese short text semantic matching based on lightweight ERNIE(2022)1 cited
• → A Language Tutoring Tool based on AI and Paraphrase Detection(2021)