UNIGE document Book Chapter
previous document  unige:15031  next document
add to browser collection
Title

Shallow Dialogue Processing Using Machine Learning Algorithms (or Not)

Authors
Lalanne, Denis
Published in B. H. and B. S. Berlin. Multimodal Interaction and Related Machine Learning Algorithms: LNCS 3361, Springer. 2004, p. 277-290
Abstract 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.
Full text
This document has no fulltext available yet, but you can contact its author by using the form below.
Structures
Research group TIM/ISSCO
Citation
(ISO format)
CLARK, Alexander et al. Shallow Dialogue Processing Using Machine Learning Algorithms (or Not). In: B. H. and B. S. Berlin (Ed.). Multimodal Interaction and Related Machine Learning Algorithms. [s.l.] : LNCS 3361, Springer, 2004. p. 277-290. https://archive-ouverte.unige.ch/unige:15031

208 hits

0 download

Update

Deposited on : 2011-05-02

Export document
Format :
Citation style :