TableQA: Question Answering on Tabular Data
This addresses the challenge for non-tech-savvy users to access insights from open datasets without specialized tools or deep dataset understanding, but it appears incremental as it focuses on demonstration and configuration aspects.
The paper tackles the problem of enabling non-technical users to analyze and search tabular data through natural language questions, resulting in a publicly available prototype system.
Tabular data is difficult to analyze and to search through, yielding for new tools and interfaces that would allow even non tech-savvy users to gain insights from open datasets without resorting to specialized data analysis tools or even without having to fully understand the dataset structure. The goal of our demonstration is to showcase answering natural language questions from tabular data, and to discuss related system configuration and model training aspects. Our prototype is publicly available and open-sourced (see https://svakulenko.ai.wu.ac.at/tableqa).