@inproceedings{shan-etal-2022-data,
    title = "Data Synthesis and Iterative Refinement for Neural Semantic Parsing without Annotated Logical Forms",
    author = "Shan, Wu  and
      Bo, Chen  and
      Xianpei, Han  and
      Le, Sun",
    editor = "Sun, Maosong  and
      Liu, Yang  and
      Che, Wanxiang  and
      Feng, Yang  and
      Qiu, Xipeng  and
      Rao, Gaoqi  and
      Chen, Yubo",
    booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
    month = oct,
    year = "2022",
    address = "Nanchang, China",
    publisher = "Chinese Information Processing Society of China",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.ccl-1.68/",
    pages = "761--773",
    language = "eng",
    abstract = "``Semantic parsing aims to convert natural language utterances to logical forms. A critical challenge for constructing semantic parsers is the lack of labeled data. In this paper, we propose a data synthesis and iterative refinement framework for neural semantic parsing, which can build semantic parsers without annotated logical forms. We first generate a naive corpus by sampling logic forms from knowledge bases and synthesizing their canonical utterances. Then, we further propose a bootstrapping algorithm to iteratively refine data and model, via a denoising language model and knowledge-constrained decoding. Experimental results show that our approach achieves competitive performance on GEO, ATIS and OVERNIGHT datasets in both unsupervised and semi-supervised data settings.''"
}