Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval

TL;DR

This paper introduces a syntax- and structure-aware dense retrieval method for open-domain table question answering, significantly improving retrieval accuracy by preserving fine-grained information and mimicking human retrieval processes.

Contribution

It proposes a novel retrieval approach that maintains syntactical and structural details during table scoring, leading to state-of-the-art results in open-domain table QA.

Findings

Achieves state-of-the-art on NQ-tables dataset.

Outperforms strong baselines on a new open-domain Text-to-SQL dataset.

Effectively preserves syntactical and structural information during retrieval.

Abstract

Open-domain table question answering aims to provide answers to a question by retrieving and extracting information from a large collection of tables. Existing studies of open-domain table QA either directly adopt text retrieval methods or consider the table structure only in the encoding layer for table retrieval, which may cause syntactical and structural information loss during table scoring. To address this issue, we propose a syntax- and structure-aware retrieval method for the open-domain table QA task. It provides syntactical representations for the question and uses the structural header and value representations for the tables to avoid the loss of fine-grained syntactical and structural information. Then, a syntactical-to-structural aggregator is used to obtain the matching score between the question and a candidate table by mimicking the human retrieval process. Experimental results show that our method achieves the state-of-the-art on the NQ-tables dataset and overwhelms strong baselines on a newly curated open-domain Text-to-SQL dataset.