CHATTER: A Character Attribution Dataset for Narrative Understanding
This provides a domain-specific benchmark for researchers in computational narrative understanding to test models on character development nuances.
The authors tackled the lack of robust benchmarks for narrative understanding by curating the CHATTER dataset, which labels 88,124 character-attribute pairs across 660 movies to evaluate character attribution tasks.
Computational narrative understanding studies the identification, description, and interaction of the elements of a narrative: characters, attributes, events, and relations. Narrative research has given considerable attention to defining and classifying character types. However, these character-type taxonomies do not generalize well because they are small, too simple, or specific to a domain. We require robust and reliable benchmarks to test whether narrative models truly understand the nuances of the character's development in the story. Our work addresses this by curating the CHATTER dataset that labels whether a character portrays some attribute for 88124 character-attribute pairs, encompassing 2998 characters, 12967 attributes and 660 movies. We validate a subset of CHATTER, called CHATTEREVAL, using human annotations to serve as a benchmark to evaluate the character attribution task in movie scripts. \evaldataset{} also assesses narrative understanding and the long-context modeling capacity of language models.