Evaluating Automatic Topic Segmentation as a Segment Retrieval Task

Abstract : Several evaluation metrics have been proposed for topic seg-mentation. Most of them rely on the paradigm that seg-mentation is mainly a task that detects boundaries, and thus are oriented on boundary detection evaluation. Nevertheless, this paradigm is not appropriate to get homogeneous chapters, which is one of the major applications of topic segmentation. For instance on Broadcast News, topic segmentation enables users to watch a chapter independently of the others. We propose to consider segmentation as a task that detects homogeneous segments, and we propose evaluation metrics oriented on segment retrieval. The proposed metrics are experimented on various TV shows from different channels. Results are analysed and discussed, highlighting their relevance.
Type de document :
Communication dans un congrès
Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.2924 - 2928, 2017, 〈http://www.interspeech2017.org〉. 〈10.21437/Interspeech.2017-1231〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01585769
Contributeur : Yannick Estève <>
Soumis le : mardi 12 septembre 2017 - 01:08:11
Dernière modification le : jeudi 21 décembre 2017 - 01:04:21
Document(s) archivé(s) le : mercredi 13 décembre 2017 - 13:34:50

Fichier

evaluating-automatic-topic.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Abdessalam Bouchekif, Delphine Charlet, Géraldine Damnati, Nathalie Camelin, Yannick Estève. Evaluating Automatic Topic Segmentation as a Segment Retrieval Task. Interspeech 2017, Aug 2017, Stockholm, Sweden. pp.2924 - 2928, 2017, 〈http://www.interspeech2017.org〉. 〈10.21437/Interspeech.2017-1231〉. 〈hal-01585769〉

Partager

Métriques

Consultations de la notice

217

Téléchargements de fichiers

66