Stories of love and violence: Zero-shot interesting events' classification for unsupervised TV series summarization

Reboud, Alison; Harrando, Ismail; Lisena, Pasquale; Troncy, Raphaël
Multimedia Systems (2023), Special Issue Paper, January 2023

In this paper, we propose an unsupervised approach to generate TV series summaries using screenplays that are composed of dialogue and scenic textual descriptions. In the last years, the creation of large language models has enabled zero-shot text classification to perform effectively in some conditions. We explore if and how such models can be used for TV series summarization by conducting experiments with varying text inputs. Our main hypothesis being that interesting moments in narratives are related to the presence of interesting events, we choose candidate labels to be events representative of two genres (crime and soap opera) and we obtain competitive results with respect to the state-of-the art baseline.

 

 

 

 

 

 

 


DOI
HAL
Type:
Journal
Date:
2023-01-11
Department:
Data Science
Eurecom Ref:
7163
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in Multimedia Systems (2023), Special Issue Paper, January 2023 and is available at : https://doi.org/10.1007/s00530-022-01040-3

PERMALINK : https://www.eurecom.fr/publication/7163