Representations for Learning to Summarize Plots

Stories can encapsulate complexity, subtlety, and nuance: all of which are implicitly contained in narrative and reasoned about automatically through the mental processes that come naturally to humans. For example, humans can package complicated plots into a relatively small set of well-recognized and meaningful linguistic terms. This summarization ability though has not been available to systems that deal with narrative and would be important in creating higher quality systems. In this paper, we describe preliminary work towards a machine learning model of plot summarization using conditional random fields and describe our own feature functions inspired by cognitive theories of narrative reasoning. Our approach allows us to learn summarization models of single character event driven narratives and automatically summarize new narratives later on.