Sabyasachee Baruah and Shrikanth Narayanan. Character Attribute Extraction from Movie Scripts Using LLMs. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8270–8275, , April 2024.
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. 1
@INPROCEEDINGS{10447353,
author={Baruah, Sabyasachee and Narayanan, Shrikanth},
booktitle={ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
title={Character Attribute Extraction from Movie Scripts Using LLMs},
year={2024},
volume={},
number={},
pages={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. 1},
keywords={Semantics;Knowledge based systems;Signal processing;Motion pictures;Information retrieval;Question answering (information retrieval);Labeling;Information Extraction;Character Attributes;Movie Screenplays},
doi={10.1109/ICASSP48485.2024.10447353},
ISSN={2379-190X},
link = {https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10447353},
month={April},}
Generated by bib2html.pl (written by Patrick Riley ) on Mon Dec 02, 2024 08:34:31