Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data
Dominik Stammbach, Maria Antoniak, Elliott Ash
Abstract
This paper shows how to use large-scale pretrained language models to extract character roles from narrative texts without domainspecific training data. Queried with a zero-shot question-answering prompt, GPT-3 can identify the hero, villain, and victim in diverse domains: newspaper articles, movie plot summaries, and political speeches.
Topics & Concepts
Character (mathematics)NarrativeHEROPlot (graphics)NewspaperComputer scienceDomain (mathematical analysis)Shot (pellet)Natural language processingPoliticsArtificial intelligenceLiteratureSociologyArtMedia studiesLawPolitical scienceMathematicsStatisticsGeometryOrganic chemistryMathematical analysisChemistryTopic ModelingNatural Language Processing TechniquesComputational and Text Analysis Methods