In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Experiments show that our approach outperforms locally normalized models on small datasets, but it does not yield improvement on a large dataset.

Authors
BibTeX

@inproceedings{huang-etal-2021-globally,
    title = "A Globally Normalized Neural Model for Semantic Parsing",
    author = {Huang, Chenyang  and
      Yang, Wei  and
      Cao, Yanshuai  and
      Za{\"\i}ane, Osmar  and
      Mou, Lili},
    booktitle = "Proceedings of the 5th Workshop on Structured Prediction for NLP (SPNLP 2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.spnlp-1.7",
    doi = "10.18653/v1/2021.spnlp-1.7",
    pages = "61--66",
    abstract = "In this paper, we propose a globally normalized model for context-free grammar (CFG)-based semantic parsing. Instead of predicting a probability, our model predicts a real-valued score at each step and does not suffer from the label bias problem. Experiments show that our approach outperforms locally normalized models on small datasets, but it does not yield improvement on a large dataset.",
}