NL4DV: A Toolkit for Generating Analytic Specifications for Data Visualization from Natural Language Queries

TL;DR

NL4DV is a Python toolkit that converts natural language queries into detailed visualization specifications, simplifying the development of natural language interfaces for data visualization without requiring NLP expertise.

Contribution

Introduces NL4DV, a toolkit that automatically generates visualization specifications from natural language queries, facilitating easier development of NLIs for data visualization.

Findings

Successfully generates Vega-Lite specifications from natural language queries.

Enables visualization development without deep NLP knowledge.

Supports multimodal input including speech for visualization commands.

Abstract

Natural language interfaces (NLIs) have shown great promise for visual data analysis, allowing people to flexibly specify and interact with visualizations. However, developing visualization NLIs remains a challenging task, requiring low-level implementation of natural language processing (NLP) techniques as well as knowledge of visual analytic tasks and visualization design. We present NL4DV, a toolkit for natural language-driven data visualization. NL4DV is a Python package that takes as input a tabular dataset and a natural language query about that dataset. In response, the toolkit returns an analytic specification modeled as a JSON object containing data attributes, analytic tasks, and a list of Vega-Lite specifications relevant to the input query. In doing so, NL4DV aids visualization developers who may not have a background in NLP, enabling them to create new visualization NLIs or incorporate natural language input within their existing systems. We demonstrate NL4DV's usage and capabilities through four examples: 1) rendering visualizations using natural language in a Jupyter notebook, 2) developing a NLI to specify and edit Vega-Lite charts, 3) recreating data ambiguity widgets from the DataTone system, and 4) incorporating speech input to create a multimodal visualization system.