Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data

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.