@inproceedings{nishida-nakayama-2018-coherence,
    title = "Coherence Modeling Improves Implicit Discourse Relation Recognition",
    author = "Nishida, Noriki  and
      Nakayama, Hideki",
    editor = "Komatani, Kazunori  and
      Litman, Diane  and
      Yu, Kai  and
      Papangelis, Alex  and
      Cavedon, Lawrence  and
      Nakano, Mikio",
    booktitle = "Proceedings of the 19th Annual {SIG}dial Meeting on Discourse and Dialogue",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/W18-5040/",
    doi = "10.18653/v1/W18-5040",
    pages = "344--349",
    abstract = "The research described in this paper examines how to learn linguistic knowledge associated with discourse relations from unlabeled corpora. We introduce an unsupervised learning method on text coherence that could produce numerical representations that improve implicit discourse relation recognition in a semi-supervised manner. We also empirically examine two variants of coherence modeling: order-oriented and topic-oriented negative sampling, showing that, of the two, topic-oriented negative sampling tends to be more effective."
}