A Unified Bayesian Model of Scripts, Frames and Language

Francis Ferraro and Benjamin Van Durme, A Unified Bayesian Model of Scripts, Frames and Language, Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, 2016.

Rights

This 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.

Subjects

learning
natural language processing
semantics
natural languge
UMBC Ebiquity Research Group

Abstract

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.