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

TL;DR

This paper demonstrates how GPT-3 can automatically identify character roles such as hero, villain, and victim in various texts without requiring any training data, using zero-shot prompting.

Contribution

It introduces a novel zero-shot method leveraging GPT-3 for extracting character roles across different narrative domains without training.

Findings

GPT-3 accurately identifies character roles in diverse texts.

The method works without any task-specific training data.

Effective across newspaper articles, movie summaries, and speeches.

Abstract

This paper shows how to use large-scale pre-trained language models to extract character roles from narrative texts without 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.