Modeling Event Salience in Narratives via Barthes’ Cardinal Functions

Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, Kentaro Inui


Abstract
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.
Anthology ID:
2020.coling-main.160
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
1784–1794
Language:
URL:
https://aclanthology.org/2020.coling-main.160
DOI:
10.18653/v1/2020.coling-main.160
Bibkey:
Cite (ACL):
Takaki Otake, Sho Yokoi, Naoya Inoue, Ryo Takahashi, Tatsuki Kuribayashi, and Kentaro Inui. 2020. Modeling Event Salience in Narratives via Barthes’ Cardinal Functions. In Proceedings of the 28th International Conference on Computational Linguistics, pages 1784–1794, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
Modeling Event Salience in Narratives via Barthes’ Cardinal Functions (Otake et al., COLING 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2020.coling-main.160.pdf
Data
BookCorpus