@inproceedings{nariyama-etal-2005-extracting,
    title = "Extracting Representative Arguments from Dictionaries for Resolving Zero Pronouns",
    author = "Nariyama, Shigeko  and
      Nichols, Eric  and
      Bond, Francis  and
      Tanaka, Takaaki  and
      Nakaiwa, Hiromi",
    booktitle = "Proceedings of Machine Translation Summit X: Papers",
    month = sep # " 13-15",
    year = "2005",
    address = "Phuket, Thailand",
    url = "https://aclanthology.org/2005.mtsummit-papers.1",
    pages = "3--10",
    abstract = "We propose a method to alleviate the problem of referential granularity for Japanese zero pronoun resolution. We use dictionary definition sentences to extract {`}representative{'} arguments of predicative definition words; e.g. {`}arrest{'} is likely to take police as the subject and criminal as its object. These representative arguments are far more informative than {`}person{'} that is provided by other valency dictionaries. They are auto-extracted using both Shallow parsing and Deep parsing for greater quality and quantity. Initial results are highly promising, obtaining more specific information about selectional preferences. An architecture of zero pronoun resolution using these representative arguments is described.",
}