Ferraro, FrancisDurme, Benjamin Van2018-10-312018-10-312016-02-12Francis Ferraro and Benjamin Van Durme, A Unified Bayesian Model of Scripts, Frames and Language, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.http://hdl.handle.net/11603/11805Proceedings of the Thirtieth AAAI Conference on Artificial IntelligenceWe present the first probabilistic model to capture all levels of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fill-more's related notion of frame, as captured in sentence-level, FrameNet semantic parses; as part of this, we resurrect the coupling among Minsky's frames, Schank's scripts and Fill-more's frames, as originally laid out by those authors. Empirically, our approach yields improved scenario representations, reflected quantitatively in lower surprisal and more coherent latent scenarios.7 pagesen-USThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.learningnatural language processingsemanticsnatural langugeUMBC Ebiquity Research GroupText