@inproceedings{radhakrishnan-etal-2020-colloql,
    title = "{C}ollo{QL}: Robust Text-to-{SQL} Over Search Queries",
    author = "Radhakrishnan, Karthik  and
      Srikantan, Arvind  and
      Lin, Xi Victoria",
    editor = "Bogin, Ben  and
      Iyer, Srinivasan  and
      Lin, Xi Victoria  and
      Radev, Dragomir  and
      Suhr, Alane  and
      Panupong  and
      Xiong, Caiming  and
      Yin, Pengcheng  and
      Yu, Tao  and
      Zhang, Rui  and
      Zhong, Victor",
    booktitle = "Proceedings of the First Workshop on Interactive and Executable Semantic Parsing",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.intexsempar-1.5/",
    doi = "10.18653/v1/2020.intexsempar-1.5",
    pages = "34--45",
    abstract = "Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling over natural language search (NLS) questions. Due to the lack of evaluation data, we curate a new dataset of NLS questions and demonstrate the efficacy of our approach. ColloQL`s superior performance extends to well-formed text, achieving an 84.9{\%} (logical) and 90.7{\%} (execution) accuracy on the WikiSQL dataset, making it, to the best of our knowledge, the highest performing model that does not use execution guided decoding."
}