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 domain-specific 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.
Anthology ID:
2022.wnu-1.6
Volume:
Proceedings of the 4th Workshop of Narrative Understanding (WNU2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
WNU
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
47–56
Language:
URL:
https://aclanthology.org/2022.wnu-1.6
DOI:
10.18653/v1/2022.wnu-1.6
Bibkey:
Cite (ACL):
Dominik Stammbach, Maria Antoniak, and Elliott Ash. 2022. Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data. In Proceedings of the 4th Workshop of Narrative Understanding (WNU2022), pages 47–56, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data (Stammbach et al., WNU 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.wnu-1.6.pdf
Video:
 https://aclanthology.org/2022.wnu-1.6.mp4