Counterfactual Explanations for Natural Language Interfaces

04/27/2022
by   George Tolkachev, et al.
0

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.

READ FULL TEXT
research
06/26/2018

Generating Counterfactual Explanations with Natural Language

Natural language explanations of deep neural network decisions provide a...
research
11/04/2019

VASTA: A Vision and Language-assisted Smartphone Task Automation System

We present VASTA, a novel vision and language-assisted Programming By De...
research
08/18/2021

I don't understand! Evaluation Methods for Natural Language Explanations

Explainability of intelligent systems is key for future adoption. While ...
research
05/22/2023

MaNtLE: Model-agnostic Natural Language Explainer

Understanding the internal reasoning behind the predictions of machine l...
research
07/14/2021

"How to best say it?" : Translating Directives in Machine Language into Natural Language in the Blocks World

We propose a method to generate optimal natural language for block place...
research
05/29/2023

Faithfulness Tests for Natural Language Explanations

Explanations of neural models aim to reveal a model's decision-making pr...
research
10/02/2021

Generating User-Centred Explanations via Illocutionary Question Answering: From Philosophy to Interfaces

We propose a new method for generating explanations with Artificial Inte...

Please sign up or login with your details

Forgot password? Click here to reset