Proceedings chapter
Open access

Word Distributions for Thematic Segmentation in a Support Vector Machine Approach

Presented at New York (USA), 8-9 June
Publication date2006

We investigate the appropriateness of using a technique based on support vector machines for identifying thematic structure of text streams. The thematic segmentation task is modeled as a binary classification problem, where the different classes correspond to the presence or the absence of a thematic boundary. Experiments are conducted with this approach by using features based on word distributions through text. We provide empirical evidence that our approach is robust, by showing good performance on three different data sets. In particular, substantial improvement is obtained over previously published results of word distribution based systems when evaluation is done on a corpus of recorded and transcribed multi-party dialogs.

Citation (ISO format)
GEORGESCUL, Maria, CLARK, Alexander, ARMSTRONG, Susan. Word Distributions for Thematic Segmentation in a Support Vector Machine Approach. In: Proceedings of the Tenth Conference on Computational Natural Language Learning (CoNLL-X). New York (USA). [s.l.] : [s.n.], 2006. p. 101–108.
Main files (1)
Proceedings chapter
  • PID : unige:3490

Technical informations

Creation10/02/2009 9:31:28 AM
First validation10/02/2009 9:31:28 AM
Update time03/14/2023 3:14:59 PM
Status update03/14/2023 3:14:59 PM
Last indexation02/12/2024 6:13:52 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack