XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis

Yingchaojie Feng, Xingbo Wang, Bo Pan, Kam Kwai Wong, Yi Ren +5 more
1/25/2023
cs.HCcs.CL

No confident code implementation found for this paper. 4 possible matches can be shown below.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

DeepVIS: Bridging Natural Language and Data Visualization Through Step-wise Reasoning

87% match2025

Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way

84% match1 repo16.0k2024

VizGen: Data Exploration and Visualization from Natural Language via a Multi-Agent AI Architecture

82% match2025

GLARE: A Natural Language Interface for Querying Global Explanations

82% match2026

EL-VIT: Probing Vision Transformer with Interactive Visualization

82% match2024

Data Formulator: AI-powered Concept-driven Visualization Authoring

81% match1 repo16.0k2023

Cite this paper

@article{feng2023xnli,
  title  = {XNLI: Explaining and Diagnosing NLI-based Visual Data Analysis},
  author = {Yingchaojie Feng and Xingbo Wang and Bo Pan and Kam Kwai Wong and Yi Ren and Shi Liu and Zihan Yan and Yuxin Ma and Huamin Qu and Wei Chen},
  year   = {2023},
  eprint = {2301.10385},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.10385v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.10385.svg)](https://codeofpaper.com/paper/2301.10385)

Discussion