XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis
This addresses the challenge for users of NLI-based visual data analysis tools in understanding and correcting errors, though it is incremental as it builds on existing NLI systems with added explainability features.
The paper tackles the problem of diagnosing visualization results in natural language interfaces (NLIs) for data analysis by introducing XNLI, an explainable system that provides explanations to help users locate issues and revise queries, with results showing it significantly enhances task accuracy without disrupting the analysis process.
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.