A Unified Bayesian Model of Scripts, Frames and Language
Links to Fileshttps://www.google.com/url?q=https://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/download/12092/11994&sa=U&ved=0ahUKEwiU64CYlJDeAhVF11kKHZAwAs0QFggEMAA&client=internal-uds-cse&cx=016314354884912110518:gwmynp16xuu&usg=AOvVaw2a2VsXzYorHgfeeGvYILz_
MetadataShow full item record
Type of Work7 pages
conference papers and proceedings pre-print
Citation of Original PublicationFrancis Ferraro and Benjamin Van Durme, A Unified Bayesian Model of Scripts, Frames and Language, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.
RightsThis 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.
natural language processing
UMBC Ebiquity Research Group
We 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.