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

arXiv: https://arxiv.org/abs/2107.14420 · HTML: https://mlsanity.com/paper/2107.14420/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2021.

## Built on by (most cited first, 7 of 7)

- [AI-Augmented Predictions: LLM Assistants Improve Human Forecasting Accuracy](https://mlsanity.com/paper/2402.07862/) (2024)
- [LightVA: Lightweight Visual Analytics with LLM Agent-Based Task Planning and Execution](https://mlsanity.com/paper/2411.05651/) (2024)
- [Conversational AI Threads for Visualizing Multidimensional Datasets](https://mlsanity.com/paper/2311.05590/) (2023)
- [Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks](https://mlsanity.com/paper/2410.03062/) (2024)
- [QUIS: Question-guided Insights Generation for Automated Exploratory Data Analysis](https://mlsanity.com/paper/2410.10270/) (2024)
- [Gen4DS: Workshop on Data Storytelling in an Era of Generative AI](https://mlsanity.com/paper/2404.01622/) (2024)
- [DataScout: Automatic Data Fact Retrieval for Statement Augmentation with an LLM-Based Agent](https://mlsanity.com/paper/2504.17334/) (2025)

## Abstract (arXiv)

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.