Abstract
In this article we address the task of automatic text structuring into linear and non-overlapping thematic episodes. Our investigation reports on the use of various lexical, acoustic and syntactic features, and makes a comparison of how these features influence performance of automatic topic segmentation. Using datasets containing multi-party meeting transcriptions, we base our experiments on a proven state-of-the-art approach using support vector classification.- Anthology ID:
- 2007.jeptalnrecital-long.1
- Volume:
- Actes de la 14ème conférence sur le Traitement Automatique des Langues Naturelles. Articles longs
- Month:
- June
- Year:
- 2007
- Address:
- Toulouse, France
- Venue:
- JEP/TALN/RECITAL
- SIG:
- Publisher:
- ATALA
- Note:
- Pages:
- 15–24
- Language:
- URL:
- https://aclanthology.org/2007.jeptalnrecital-long.1
- DOI:
- Cite (ACL):
- Maria Georgescul, Alexander Clarck, and Susan Armstrong. 2007. Exploiting structural meeting-specific features for topic segmentation. In Actes de la 14ème conférence sur le Traitement Automatique des Langues Naturelles. Articles longs, pages 15–24, Toulouse, France. ATALA.
- Cite (Informal):
- Exploiting structural meeting-specific features for topic segmentation (Georgescul et al., JEP/TALN/RECITAL 2007)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2007.jeptalnrecital-long.1.pdf