Proceedings chapter
OA Policy
English

Exploiting Structural Meeting-Specific Features for Topic Segmentation

Presented atToulouse (France)
Published inActes de TALN/RECITAL, p. 15-24
Publication date2007
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.

Citation (ISO format)
GEORGESCUL, Maria, CLARK, Alexander, ARMSTRONG, Susan. Exploiting Structural Meeting-Specific Features for Topic Segmentation. In: Actes de TALN/RECITAL. Toulouse (France). [s.l.] : [s.n.], 2007. p. 15–24.
Main files (1)
Proceedings chapter
accessLevelPublic
Identifiers
  • PID : unige:3463
626views
400downloads

Technical informations

Creation02/10/2009 09:28:58
First validation02/10/2009 09:28:58
Update time14/03/2023 15:14:53
Status update14/03/2023 15:14:53
Last indexation29/10/2024 12:18:32
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack