Book chapter

Shallow Dialogue Processing Using Machine Learning Algorithms (or Not)

Published inMultimodal Interaction and Related Machine Learning Algorithms, Editors B. H. and B. S. Berlin, p. 277-290
PublisherLNCS 3361, Springer
Publication date2004

This paper presents a shallow dialogue analysis model, aimed at human-human dialogues in the context of staff or business meetings. Four components of the model are defined, and several machine learning techniques are used to extract features from dialogue transcripts: maximum entropy classifiers for dialogue acts, latent semantic analysis for topic segmentation, or decision tree classifiers for discourse markers. A rule-based approach is proposed for solving cross-modal references to meeting documents. The methods are trained and evaluated thanks to a common data set and annotation format. The integration of the components into an automated shallow dialogue parser opens the way to multimodal meeting processing and retrieval applications.

Research group
Citation (ISO format)
CLARK, Alexander et al. Shallow Dialogue Processing Using Machine Learning Algorithms (or Not). In: Multimodal Interaction and Related Machine Learning Algorithms. [s.l.] : LNCS 3361, Springer, 2004. p. 277–290.
  • PID : unige:15031

Technical informations

Creation04/13/2011 9:31:00 PM
First validation04/13/2011 9:31:00 PM
Update time03/14/2023 4:51:07 PM
Status update03/14/2023 4:51:07 PM
Last indexation01/15/2024 10:19:50 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack