Summary of Automated Question Generation on Tabular Data For Conversational Data Exploration, by Ritwik Chaudhuri et al.
Automated Question Generation on Tabular Data for Conversational Data Exploration
by Ritwik Chaudhuri, Rajmohan C, Kirushikesh DB, Arvind Agarwal
First submitted to arxiv on: 10 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to exploratory data analysis is introduced, focusing on conversational data exploration that enables non-technical users to analyze datasets without requiring deep technical knowledge. The system recommends interesting questions in natural language based on relevant slices of the dataset. This is achieved by identifying interesting columns and column combinations using various measures of interest. A fine-tuned pre-trained language model (T5) generates natural language questions, which are then slotted with values from the dataset and ranked for recommendations. The proposed system is demonstrated to be effective in a conversational setting using real datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a way for people without technical expertise to explore data without needing to understand complex data analysis techniques. It does this by recommending questions that are relevant to the data, based on interesting parts of the dataset. This approach uses a special language model to generate questions and then fills in the answers from the data. The result is a system that makes it easier for non-technical users to gain insights from data. |
Keywords
» Artificial intelligence » Language model » T5
