MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering

Abstract

Recent advances in tabular question answering (QA) with large language models are constrained in their coverage and only answer questions over a single table. However, real-world queries are complex in nature, often over multiple tables in a relational database or web page. Single table questions do not involve common table operations such as set operations, Cartesian products (joins), or nested queries. Furthermore, multi-table operations often result in a tabular output, which necessitates table generation capabilities of tabular QA models. To fill this gap, we propose a new task of answering questions over multiple tables. Our model, MultiTabQA, not only answers questions over multiple tables, but also generalizes to generate tabular answers. To enable effective training, we build a pre-training dataset comprising of 132,645 SQL queries and tabular answers. Further, we evaluate the generated tables by introducing table-specific metrics of varying strictness assessing various levels of granularity of the table structure. MultiTabQA outperforms state-of-the-art single table QA models adapted to a multi-table QA setting by finetuning on three datasets: Spider, Atis and GeoQuery.

arXiv commentAccepted at ACL-2023

References in corpus (7)

• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• TAPEX: Table Pre-training via Learning a Neural SQL Executor
• Investigating the Limitations of Transformers with Simple Arithmetic Tasks
• Parameter-Efficient Abstractive Question Answering over Tables or Text
• HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation
• A Survey on Table Question Answering: Recent Advances
• Enhancing Tabular Reasoning with Pattern Exploiting Training