Inferring Interpersonal Relations in Narrative Summaries
This work addresses the challenge of understanding interpersonal dynamics in narratives, which is incremental as it builds on existing methods with specific improvements.
The paper tackled the problem of inferring relationship polarity between people in narrative summaries by developing a joint structured prediction model that uses linguistic, semantic, and social community features, achieving over 30% error reduction on a dataset of movie summaries.
Characterizing relationships between people is fundamental for the understanding of narratives. In this work, we address the problem of inferring the polarity of relationships between people in narrative summaries. We formulate the problem as a joint structured prediction for each narrative, and present a model that combines evidence from linguistic and semantic features, as well as features based on the structure of the social community in the text. We also provide a clustering-based approach that can exploit regularities in narrative types. e.g., learn an affinity for love-triangles in romantic stories. On a dataset of movie summaries from Wikipedia, our structured models provide more than a 30% error-reduction over a competitive baseline that considers pairs of characters in isolation.