Multi-view hidden markov perceptrons

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

Discriminative learning techniques for sequential data have proven to be more effective than generative models for named entity recognition, information extraction, and other tasks of discrimination. However, semi-supervised learning mechanisms that utilize inexpensive unlabeled sequences in addition to few labeled sequences - such as the Baum-Welch algorithm - are available only for generative models. The multi-view approach is based on the principle of maximizing the consensus among multiple independent hypotheses; we develop this principle into a semisupervised hidden Markov perceptron algorithm. Experiments reveal that the resulting procedure utilizes unlabeled data effectively and discriminates more accurately than its purely supervised counterparts.
OriginalspracheEnglisch
TitelLernen, Wissensentdeckung und Adaptivitat, LWA 2005
HerausgeberMathias Bauer, Boris Brandherm, Johannes Fürnkranz, Gunter Grieser, Andreas Hotho, Andreas Jedlitschka, Alexander Kröner
Anzahl der Seiten5
ErscheinungsortSaarbrücken
VerlagGesellschaft für Informatik e.V.
Erscheinungsdatum2005
Seiten134-138
PublikationsstatusErschienen - 2005
Extern publiziertJa
VeranstaltungLernen, Wissensentdeckung und Adaptivität - LWA 2005 - Universität des Saarlandes, Saarbrücken, Deutschland
Dauer: 10.10.200512.10.2005
http://www.dfki.de/lwa2005/

Dokumente