Summary of Retqa: a Large-scale Open-domain Tabular Question Answering Dataset For Real Estate Sector, by Zhensheng Wang et al.
RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector
by Zhensheng Wang, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia
First submitted to arxiv on: 13 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers address the lack of datasets for automated question-answering systems in the real estate market by introducing RETQA, a large-scale open-domain Chinese Tabular Question Answering dataset. The dataset comprises 4,932 tables and 20,762 question-answer pairs across 16 sub-fields within three major domains. To tackle challenges posed by long-table structures, open-domain retrieval, and multi-domain queries, the authors propose the SLUTQA framework, which integrates large language models with spoken language understanding tasks to enhance retrieval and answering accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The real estate market needs better tools for answering questions about property details, market trends, and price fluctuations. To help, researchers created a big dataset of tables and questions that can be answered using these tables. The dataset has lots of challenges, like having many tables with lots of information, needing to find the right answer from the internet, and answering questions from different areas like property prices or company finances. |
Keywords
» Artificial intelligence » Language understanding » Question answering
