Paper: Statistical Script Learning with Multi-Argument Events

ACL ID E14-1024
Title Statistical Script Learning with Multi-Argument Events
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2014

Scripts represent knowledge of stereotyp- ical event sequences that can aid text un- derstanding. Initial statistical methods have been developed to learn probabilis- tic scripts from raw text corpora; how- ever, they utilize a very impoverished rep- resentation 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. Ex- periments on a large corpus using the task of inferring held-out events (the ?narrative cloze evaluation?) demonstrate that mod- eling multi-argument events improves pre- dictive accuracy.