Talk2Data: A Natural Language Interface for Exploratory Visual Analysis via Question Decomposition

TL;DR

Talk2Data is a natural language interface that enables users to ask complex exploratory visual analysis questions, decomposing them into simpler queries and providing interpretative visual answers, thus enhancing data exploration.

Contribution

The paper introduces Talk2Data, a novel NLI that handles complex questions in visual data analysis by question decomposition and visual narration, advancing beyond existing simple-query systems.

Findings

Effective decomposition of complex questions into simple ones.

Improved user experience in exploratory data analysis.

Positive evaluation results from user studies.

Abstract

Through a natural language interface (NLI) for exploratory visual analysis, users can directly "ask" analytical questions about the given tabular data. This process greatly improves user experience and lowers the technical barriers of data analysis. Existing techniques focus on generating a visualization from a concrete question. However, complex questions, requiring multiple data queries and visualizations to answer, are frequently asked in data exploration and analysis, which cannot be easily solved with the existing techniques. To address this issue, in this paper, we introduce Talk2Data, a natural language interface for exploratory visual analysis that supports answering complex questions. It leverages an advanced deep-learning model to resolve complex questions into a series of simple questions that could gradually elaborate on the users' requirements. To present answers, we design a set of annotated and captioned visualizations to represent the answers in a form that supports interpretation and narration. We conducted an ablation study and a controlled user study to evaluate Talk2Data's effectiveness and usefulness.