@inproceedings{li-etal-2019-neural-chinese,
    title = "Neural {C}hinese Address Parsing",
    author = "Li, Hao  and
      Lu, Wei  and
      Xie, Pengjun  and
      Li, Linlin",
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/N19-1346/",
    doi = "10.18653/v1/N19-1346",
    pages = "3421--3431",
    abstract = "This paper introduces a new task {--} Chinese address parsing {--} the task of mapping Chinese addresses into semantically meaningful chunks. While it is possible to model this problem using a conventional sequence labelling approach, our observation is that there exist complex dependencies between labels that cannot be readily captured by a simple linear-chain structure. We investigate neural structured prediction models with latent variables to capture such rich structural information within Chinese addresses. We create and publicly release a new dataset consisting of 15K Chinese addresses, and conduct extensive experiments on the dataset to investigate the model effectiveness and robustness. We release our code and data at \url{http://statnlp.org/research/sp}."
}