Statistical Script Learning with Multi-Argument Events (2014)
Scripts represent knowledge of stereotypical event sequences that can aid text understanding. Initial statistical methods have been developed to learn probabilistic scripts from raw text corpora; however, they utilize a very impoverished representation of events, consisting of a verb and one dependent argument. We present a script learning approach that employs events with multiple arguments. Unlike previous work, we model the interactions between multiple entities in a script. Experiments on a large corpus using the task of inferring held-out events (the "narrative cloze evaluation") demonstrate that modeling multi-argument events improves predictive accuracy.
In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2014), pp. 220--229, Gothenburg, Sweden, April 2014.

Raymond J. Mooney Faculty mooney [at] cs utexas edu
Karl Pichotta Ph.D. Student pichotta [at] cs utexas edu