Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data

Moshe Hazoom, Vibhor Malik, Ben Bogin

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

    Abstract

    Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12, 023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.

    Original languageEnglish
    Title of host publicationNLP4Prog 2021 - 1st Workshop on Natural Language Processing for Programming, Proceedings of the Workshop
    EditorsRoyi Lachmy, Ziyu Yao, Greg Durrett, Milos Gligoric, Junyi Jessy Li, Ray Mooney, Graham Neubig, Yu Su, Huan Sun, Reut Tsarfaty
    PublisherAssociation for Computational Linguistics (ACL)
    Pages77-87
    Number of pages11
    ISBN (Electronic)9781954085640
    StatePublished - 2021
    Event1st Workshop on Natural Language Processing for Programming, NLP4Prog 2021 - Virtual, Bangkok, Thailand
    Duration: 6 Aug 2021 → …

    Publication series

    NameNLP4Prog 2021 - 1st Workshop on Natural Language Processing for Programming, Proceedings of the Workshop

    Conference

    Conference1st Workshop on Natural Language Processing for Programming, NLP4Prog 2021
    Country/TerritoryThailand
    CityVirtual, Bangkok
    Period6/08/21 → …

    Fingerprint

    Dive into the research topics of 'Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data'. Together they form a unique fingerprint.

    Cite this