TableQA: Question Answering on Tabular Data

TL;DR

TableQA introduces a system for natural language question answering on tabular data, enabling non-expert users to extract insights without specialized tools, with an open-source prototype available.

Contribution

It presents a novel system for natural language querying of tables, including system configuration and training aspects, and provides an open-source implementation.

Findings

Prototype demonstrates effective question answering on tables

System configuration and training are discussed in detail

Open-source availability facilitates adoption and further research

Abstract

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).