NAACL 2021long49 citations

NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction

Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Hassan Awadallah

Abstract

We study semantic parsing in an interactive setting in which users correct errors with natural language feedback. We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors. We show that NL-EDIT can boost the accuracy of existing text-to-SQL parsers by up to 20% with only one turn of correction. We analyze the limitations of the model and discuss directions for improvement and evaluation. The code and datasets used in this paper are publicly available at http://aka.ms/NLEdit.

BibTeX
@inproceedings{elgohary-etal-2021-nl,
    title = "{NL}-{EDIT}: Correcting Semantic Parse Errors through Natural Language Interaction",
    author = "Elgohary, Ahmed  and
      Meek, Christopher  and
      Richardson, Matthew  and
      Fourney, Adam  and
      Ramos, Gonzalo  and
      Awadallah, Ahmed Hassan",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.naacl-main.444/",
    doi = "10.18653/v1/2021.naacl-main.444",
    pages = "5599--5610"
}
NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction · NAACL 2021