@inproceedings{he-etal-2018-jointly,
    title = "Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling",
    author = "He, Luheng  and
      Lee, Kenton  and
      Levy, Omer  and
      Zettlemoyer, Luke",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P18-2058/",
    doi = "10.18653/v1/P18-2058",
    pages = "364--369",
    abstract = "Recent BIO-tagging-based neural semantic role labeling models are very high performing, but assume gold predicates as part of the input and cannot incorporate span-level features. We propose an end-to-end approach for jointly predicting all predicates, arguments spans, and the relations between them. The model makes independent decisions about what relationship, if any, holds between every possible word-span pair, and learns contextualized span representations that provide rich, shared input features for each decision. Experiments demonstrate that this approach sets a new state of the art on PropBank SRL without gold predicates."
}