Skip to main navigation Skip to search Skip to main content

MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL

  • Harbin Institute of Technology
  • Individual Researcher

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The open-domain text-to-SQL task aims to retrieve question-relevant tables from massive databases and generate SQL. However, the performance of current methods is constrained by single-hop retrieval, and existing multi-hop retrieval of open-domain question answering is not directly applicable due to the tendency to retrieve tables similar to the retrieved ones but irrelevant to the question. Since the questions in text-to-SQL usually contain all required information, while previous multi-hop retrieval supplements the questions with retrieved documents. Therefore, we propose the multi-hop table retrieval with removal (MURRE), which removes previously retrieved information from the question to guide the retriever towards unretrieved relevant tables. Our experiments on two open-domain text-to-SQL datasets demonstrate an average improvement of 5.7% over the previous state-of-the-art results.

Original languageEnglish
Title of host publicationMain Conference
EditorsOwen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
PublisherAssociation for Computational Linguistics (ACL)
Pages5789-5806
Number of pages18
ISBN (Electronic)9798891761964
StatePublished - 2025
Event31st International Conference on Computational Linguistics, COLING 2025 - Abu Dhabi, United Arab Emirates
Duration: 19 Jan 202524 Jan 2025

Publication series

NameProceedings - International Conference on Computational Linguistics, COLING
ISSN (Print)2951-2093

Conference

Conference31st International Conference on Computational Linguistics, COLING 2025
Country/TerritoryUnited Arab Emirates
CityAbu Dhabi
Period19/01/2524/01/25

Fingerprint

Dive into the research topics of 'MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL'. Together they form a unique fingerprint.

Cite this