Skip to content

Detail of publication


Švec Jan and Jurčíček Filip : Extended Hidden Vector State Parser . Text, Speech and Dialogue, p. 403-410, Springer, Plzeň, 2009.


The key component of a spoken dialogue system is a spoken understanding module. There are many approaches to the understanding module design and one of the most perspective is a statistical based semantic parsing. This paper presents a combination of a set of modications of the hidden vector state (HVS) parser which is a very popular method for the statistical semantic parsing. This paper describes the combination of three modications of the basic HVS parser and proves that these changes are almost independent. The proposed changes to the HVS parser form the extended hidden vector state parser (EHVS). The performance of the parser increases from 47.7% to 63.1% under the exact match between the reference and the hypothesis semantic trees evaluated using Human-Human Train Timetable corpus. In spite of increased performance, the complexity of the EHVS parser increases only linearly. Therefore the EHVS parser preserves simplicity and robustness of the baseline HVS parser.

Detail of publication

Title: Extended Hidden Vector State Parser
Author: Švec Jan ; Jurčíček Filip
Language: English
Year: 2009
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Text, Speech and Dialogue
Page: 403 - 410
ISBN: 978-3-642-04207-2
Publisher: Springer
Address: Plzeň
2011-03-15 16:21:45 / 2011-03-15 16:21:45 / 1


semantic parsing, dialogue systems, HVS parser


 author = {\v{S}vec Jan and Jur\v{c}\'{i}\v{c}ek Filip},
 title = {Extended Hidden Vector State Parser},
 year = {2009},
 publisher = {Springer},
 journal = {Text, Speech and Dialogue},
 address = {Plze\v{n}},
 pages = {403-410},
 ISBN = {978-3-642-04207-2},
 note = {LNCS 5729, ISSN 0302-9743
z\'{a}znam byl UK p\v{r}e\v{r}azen a dopln\v{e}n o UT ISI na \v{z}\'{a}dost prof. Psutky},
 url = {},