@inproceedings{krishnamurthy-etal-2017-neural,
    title = "Neural Semantic Parsing with Type Constraints for Semi-Structured Tables",
    author = "Krishnamurthy, Jayant  and
      Dasigi, Pradeep  and
      Gardner, Matt",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D17-1160/",
    doi = "10.18653/v1/D17-1160",
    pages = "1516--1526",
    abstract = "We present a new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables. Our parser is an encoder-decoder neural network with two key technical innovations: (1) a grammar for the decoder that only generates well-typed logical forms; and (2) an entity embedding and linking module that identifies entity mentions while generalizing across tables. We also introduce a novel method for training our neural model with question-answer supervision. On the WikiTableQuestions data set, our parser achieves a state-of-the-art accuracy of 43.3{\%} for a single model and 45.9{\%} for a 5-model ensemble, improving on the best prior score of 38.7{\%} set by a 15-model ensemble. These results suggest that type constraints and entity linking are valuable components to incorporate in neural semantic parsers."
}