# Modeling Event Salience in Narratives via Barthes' Cardinal Functions

arXiv: https://arxiv.org/abs/2011.01785 · HTML: https://mlsanity.com/paper/2011.01785/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 6 of 6)

- [Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories](https://mlsanity.com/paper/2109.03754/) (2021)
- [Prosody Analysis of Audiobooks](https://mlsanity.com/paper/2310.06930/) (2023)
- [Contrastive Learning with Narrative Twins for Modeling Story Salience](https://mlsanity.com/paper/2601.07765/) (2026)
- [Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis](https://mlsanity.com/paper/2506.12189/) (2025)
- [Story Ribbons: Reimagining Storyline Visualizations with Large Language Models](https://mlsanity.com/paper/2508.06772/) (2025)
- [Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering](https://mlsanity.com/paper/2610.18121/) (2026)

## Abstract (arXiv)

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.