Use of negative examples in training the HVS semantic model

Authors:
Filip Jurčíček;Jan Švec;Jiří Zahradil;Libor Jelínek
Affiliations:
Center of Applied Cybernetics, University of West Bohemia, Pilsen, Czech Republic;Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic;Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic;Department of Cybernetics, University of West Bohemia, Pilsen, Czech Republic
Venue:
TSD'06 Proceedings of the 9th international conference on Text, Speech and Dialogue
Year:
2006

Citing 2
Cited 0

Procedure for quantitatively comparing the syntactic coverage of English grammars

HLT '91 Proceedings of the workshop on Speech and Natural Language
Statistical methods for speech recognition

Statistical methods for speech recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes use of negative examples in training the HVS semantic model We present a novel initialization of the lexical model using negative examples extracted automatically from a semantic corpus as well as description of an algorithm for extraction these examples We evaluated the use of negative examples on a closed domain human-human train timetable dialogue corpus We significantly improved the standard PARSEVAL scores of the baseline system The labeled F-measure (LF) was increased from 45.4% to 49.1%.