Shallow Dialogue Processing Using Machine Learning Algorithms (or Not)
|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.|
This document has no fulltext available yet, but you can contact its author by using the form below.
|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|