Use of Negative Examples in Training the HVS Semantic Model

Use of Negative Examples in Training the HVS Semantic Model

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 o...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jurčíček, Filip, Švec, Jan, Zahradil, Jiří, Jelínek, Libor
Format: Buchkapitel
Sprache:eng
Schlagworte:
Applied sciences
Artificial intelligence
Computer science
control theory
systems
Exact sciences and technology
Operational research and scientific management
Operational research. Management science
Scheduling, sequencing
Speech and sound recognition and synthesis. Linguistics
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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%.
ISSN:0302-9743
1611-3349
DOI:10.1007/11846406_76