Skip N-grams and Ranking Functions for Predicting Script Events

Abstract

In this paper, we extend current state-of-theart research on unsupervised acquisition of scripts, that is, stereotypical and frequently observed sequences of events. We design, evaluate and compare different methods for constructing models for script event prediction: given a partial chain of events in a script, predict other events that are likely to… (More)

Topics

7 Figures and Tables

Statistics

050100201520162017
Citations per Year

Citation Velocity: 35

Averaging 35 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.

Slides referencing similar topics