DocumentCode
3627814
Title
Extension of HVS semantic parser by allowing left-right branching
Author
Filip Jurcicek;Jan Svec;Ludek Muller
Author_Institution
Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czech Republic
fYear
2008
Firstpage
4993
Lastpage
4996
Abstract
The hidden vector state (HVS) parser is a popular method for semantic parsing. It is used in the language understanding module of the statistical based spoken dialog system. This paper presents an extension of the HVS semantic parser. It enables the parser to generate broader class of semantic trees. This modification can be used to improve the performance of the parser by generating not only the right-branching trees (like original HVS parser) but also limited left-branching trees and their combinations. The extension retains simplicity and properties of the original HVS parser. We tested the method on Czech human-human train timetable corpus. The modified HVS parser yields statistically significant improvement. The accuracy of the system increased from 50.4% to 58.3% absolutely.
Keywords
"Natural languages","Information retrieval","Automata","Cybernetics","Testing","Cultural differences","Global communication","Maximum a posteriori estimation","Probability","Helium"
Publisher
ieee
Conference_Titel
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
ISSN
1520-6149
Print_ISBN
978-1-4244-1483-3
Electronic_ISBN
2379-190X
Type
conf
DOI
10.1109/ICASSP.2008.4518779
Filename
4518779
Link To Document