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

2024-12-13

arXiv.org

AI Summary

To address the lack of large-scale Chinese table-based question answering (QA) datasets in the real estate domain, this paper introduces RETQA—the first open-domain Chinese real estate table QA dataset—comprising 4,932 tables and 20,762 QA pairs spanning 16 subdomains, including property information, developer financials, and land auctions. To tackle challenges in long-table understanding, open-domain retrieval, and multi-domain query interpretation, we propose SLUTQA, a novel framework integrating large language model (LLM)-based in-context learning (ICL), structured table understanding, cross-domain semantic retrieval, and colloquial question parsing. Experiments demonstrate that SLUTQA achieves significant improvements in QA accuracy on RETQA. Both the dataset and implementation code are publicly released to advance the development and practical deployment of intelligent real estate QA systems.

Technology Category

• Natural Language Processing: Question Answering
• Knowledge Representation and Reasoning: Qualitative Reasoning
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web question answering
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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}.

Problem

• Real Estate
• Chinese Tabular QA
• Dataset Limitations

Innovation

• RETQA
• SLUTQA
• Real Estate Table Question Answering