@inproceedings{misra-etal-2018-policy,
    title = "Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations",
    author = "Misra, Dipendra  and
      Chang, Ming-Wei  and
      He, Xiaodong  and
      Yih, Wen-tau",
    editor = "Riloff, Ellen  and
      Chiang, David  and
      Hockenmaier, Julia  and
      Tsujii, Jun{'}ichi",
    booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
    month = oct # "-" # nov,
    year = "2018",
    address = "Brussels, Belgium",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D18-1266/",
    doi = "10.18653/v1/D18-1266",
    pages = "2442--2452",
    abstract = "Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm. We propose effective and general solutions to each of them. Using policy shaping, we bias the search procedure towards semantic parses that are more compatible to the text, which provide better supervision signals for training. In addition, we propose an update equation that generalizes three different families of learning algorithms, which enables fast model exploration. When experimented on a recently proposed sequential question answering dataset, our framework leads to a new state-of-the-art model that outperforms previous work by 5.0{\%} absolute on exact match accuracy."
}