RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector

TL;DR

RETQA is a large-scale Chinese dataset for real estate tabular question answering, introducing new challenges like long tables and multi-domain queries, and proposing the SLUTQA framework to improve model performance.

Contribution

This paper introduces RETQA, the first large-scale open-domain Chinese tabular QA dataset for real estate, and proposes SLUTQA, a framework combining language models with spoken language understanding.

Findings

SLUTQA significantly improves large language models' performance on RETQA.

RETQA presents challenges like long tables and multi-domain queries, advancing QA research.

The dataset and framework are publicly available for further research.

Abstract

The real estate market relies heavily on structured data, such as property details, market trends, and price fluctuations. However, the lack of specialized Tabular Question Answering datasets in this domain limits the development of automated question-answering systems. To fill this gap, we introduce RETQA, the first large-scale open-domain Chinese Tabular Question Answering dataset for Real Estate. RETQA comprises 4,932 tables and 20,762 question-answer pairs across 16 sub-fields within three major domains: property information, real estate company finance information and land auction information. Compared with existing tabular question answering datasets, RETQA poses greater challenges due to three key factors: long-table structures, open-domain retrieval, and multi-domain queries. To tackle these challenges, we propose the SLUTQA framework, which integrates large language models with spoken language understanding tasks to enhance retrieval and answering accuracy. Extensive experiments demonstrate that SLUTQA significantly improves the performance of large language models on RETQA by in-context learning. RETQA and SLUTQA provide essential resources for advancing tabular question answering research in the real estate domain, addressing critical challenges in open-domain and long-table question-answering. The dataset and code are publicly available at \url{https://github.com/jensen-w/RETQA}.