Boosting with prior knowledge for call classification

The use of boosting for call classification in spoken language understanding is described in this paper. An extension to the AdaBoost algorithm is presented that permits the incorporation of prior knowledge of the application as a means of compensating for the large dependence on training data. We g...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on speech and audio processing 2005-03, Vol.13 (2), p.174-181
Hauptverfasser:	Schapire, R.E., Rochery, M., Rahim, M., Gupta, N.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Applied sciences Boosting call classification Classification Convergence dialogue systems Exact sciences and technology Humans Information, signal and communications theory Learning systems Loss measurement Natural languages Performance enhancement prior knowledge Robustness Signal processing Speech Speech processing Speech recognition spoken language understanding Telecommunications and information theory Text categorization Training Training data
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The use of boosting for call classification in spoken language understanding is described in this paper. An extension to the AdaBoost algorithm is presented that permits the incorporation of prior knowledge of the application as a means of compensating for the large dependence on training data. We give a convergence result for the algorithm, and we describe experiments on four datasets showing that prior knowledge can substantially improve classification performance.
ISSN:	1063-6676 2329-9290 1558-2353 2329-9304
DOI:	10.1109/TSA.2004.840937