# Automated Question Generation on Tabular Data for Conversational Data Exploration

arXiv: https://arxiv.org/abs/2407.12859 · HTML: https://mlsanity.com/paper/2407.12859/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 27 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 3 of 3)

- [Unsupervised Multi-hop Question Answering by Question Generation](https://mlsanity.com/paper/2010.12623/) (2020)
- [A Model-based Chatbot Generation Approach to Converse with Open Data Sources](https://mlsanity.com/paper/2007.10503/) (2020)
- [Learning Interesting Categorical Attributes for Refined Data Exploration](https://mlsanity.com/paper/1711.10933/) (2017)

## Built on by (most cited first, 1 of 1)

- [From Question-First to Analyst-First: Domain-Expert Skills and Verified Knowledge Compilation for Proactive Enterprise Analytics](https://mlsanity.com/paper/2608.28594/) (2026)

## Abstract (arXiv)

Exploratory data analysis (EDA) is an essential step for analyzing a dataset to derive insights. Several EDA techniques have been explored in the literature. Many of them leverage visualizations through various plots. But it is not easy to interpret them for a non-technical user, and producing appropriate visualizations is also tough when there are a large number of columns. Few other works provide a view of some interesting slices of data but it is still difficult for the user to draw relevant insights from them. Of late, conversational data exploration is gaining a lot of traction among non-technical users. It helps the user to explore the dataset without having deep technical knowledge about the data. Towards this, we propose a system that recommends interesting questions in natural language based on relevant slices of a dataset in a conversational setting. Specifically, given a dataset, we pick a select set of interesting columns and identify interesting slices of such columns and column combinations based on few interestingness measures. We use our own fine-tuned variation of a pre-trained language model(T5) to generate natural language questions in a specific manner. We then slot-fill values in the generated questions and rank them for recommendations. We show the utility of our proposed system in a coversational setting with a collection of real datasets.