XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

TL;DR

XNLI is an explainable natural language interface for visual data analysis that helps users diagnose and revise queries effectively, improving accuracy and usability.

Contribution

The paper introduces XNLI, a system with provenance and hint generators, to explain and diagnose NLI-based visual data analysis, which is a novel approach.

Findings

Significantly improves task accuracy

Enhances usability through interactive explanations

Effective in diagnosing and revising queries

Abstract

Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint Generator to provide query revision hints based on the analysis of user queries and interactions. Two usage scenarios of XNLI and a user study verify the effectiveness and usability of the system. Results suggest that XNLI can significantly enhance task accuracy without interrupting the NLI-based analysis process.