Character Attribute Extraction from Movie Scripts Using LLMs
Authors:
- 14 April 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8270-8275
Abstract
Narrative understanding is an integrative task of studying characters, plots, events, and relations in a story. It involves natural language processing tasks such as named entity recognition and coreference resolution to identify the characters, semantic role labeling and argument mining to find character actions and events, information extraction and question answering to describe character attributes, causal analysis to relate different events, and summarization to find the main storyline. In this work, we aim to formally operationalize the task of character attribute extraction, motivated by analyzing inclusive character representations and portrayals. We focus on a mix of static and dynamic attribute types that require varying context sizes for their accurate retrieval. We use automated screenplay parsing, entity recognition, and external knowledge bases to collect character descriptions from movie scripts, and explore different prompting strategies (zero-shot, few-shot, and chain-of-thought) to leverage large language models for attribute extraction. 1Keywords
This publication has 14 references indexed in Scilit:
- Computational Understanding of Narratives: A SurveyIEEE Access, 2022
- Representation of professions in entertainment media: Insights into frequency and sentiment trends through computational text analysisPLOS ONE, 2022
- MBTI Personality Prediction for Fictional Characters Using Movie Scripts2022
- Salience-Aware Event Chain Modeling for Narrative Understanding2021
- Narrative Theory for Computational Narrative Understanding2021
- Annotation and Evaluation of Coreference Resolution in Screenplays2021
- TellMeWhy: A Dataset for Answering Why-Questions in Narratives2021
- Story Realization: Expanding Plot Events into SentencesProceedings of the AAAI Conference on Artificial Intelligence, 2020
- Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts2020
- Extraction and Analysis of Fictional Character NetworksACM Computing Surveys, 2019