Exploiting Structural Meeting-Specific Features for Topic Segmentation
Maria Georgescul, Alexander Clarck, Susan Armstrong · Archive ouverte UNIGE (University of Geneva) · 2007
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.