Events in a narrative differ in salience: some are more important to the story than others. Estimating event salience is useful for tasks such as story generation, and as a tool for text analysis in narratology and folkloristics. To compute event salience without any annotations, we adopt Barthes' definition of event salience and propose several unsupervised methods that require only a pre-trained language model. Evaluating the proposed methods on folktales with event salience annotation, we show that the proposed methods outperform baseline methods and find fine-tuning a language model on narrative texts is a key factor in improving the proposed methods.
@article{arxiv.2011.01785,
title = {Modeling Event Salience in Narratives via Barthes' Cardinal Functions},
author = {Takaki Otake and Sho Yokoi and Naoya Inoue and Ryo Takahashi and Tatsuki Kuribayashi and Kentaro Inui},
journal= {arXiv preprint arXiv:2011.01785},
year = {2020}
}