Script Parsing with Hierarchical Sequence Modelling

Abstract

Scripts (Schank and Abelson, 1977) capture commonsense knowledge about everyday activities and their participants. Script knowledge has been shown to be useful in a number of NLP tasks, such as referent prediction, discourse classification, and story generation. A crucial step for the exploitation of script knowledge is script parsing, the task of tagging a text with the events and participants from a certain activity. This task is challenging: It requires information both about the ways events and participants are usually realized in surface language as well as the order in which they occur in the world. We show how to do accurate script parsing with a hierarchical sequence model. Our model improves the state of the art of event parsing by over 16 points F-score and, for the first time, accurately tags script participants.