Other formats:
BibTeX
LaTeX
RIS
@inproceedings{806006,
author = {Kovář, Vojtěch and Horák, Aleš and Jakubíček, Miloš},
address = {Ostrava},
booktitle = {Proceedings of ELNET 2008},
keywords = {electrical power networks;czech domain-specific resources;syntax analysis;text corpora},
language = {eng},
location = {Ostrava},
isbn = {978-80-248-1875-7},
pages = {72-80},
publisher = {Faculty of Electrical Engineering and Computer Science, VŠB - Technical University of Ostrava},
title = {Power Networks Dialogs - Enhancing Domain-Specific Text Processing Techniques and Resources},
year = {2008}
}
TY - JOUR
ID - 806006
AU - Kovář, Vojtěch - Horák, Aleš - Jakubíček, Miloš
PY - 2008
TI - Power Networks Dialogs - Enhancing Domain-Specific Text Processing Techniques and Resources
PB - Faculty of Electrical Engineering and Computer Science, VŠB - Technical University of Ostrava
CY - Ostrava
SN - 9788024818757
KW - electrical power networks;czech domain-specific resources;syntax analysis;text corpora
N2 - In this paper, we describe the process of development of the analytical approaches adapted for the work with technical texts specialized at the domain of electrical power networks (EPN) topics. The process includes improving the quality of the EPN resources. The new data represent one of the largest domain specific corpora containing more than 5 million of text tokens. We show the details of building a new the large domain-specific corpus, its analysis and further processing such as filtering, morphological and syntactical analysis and phrase detection and present, how they help to improve the dialog system.
ER -
KOVÁŘ, Vojtěch, Aleš HORÁK and Miloš JAKUBÍČEK. Power Networks Dialogs - Enhancing Domain-Specific Text Processing Techniques and Resources. In \textit{Proceedings of ELNET 2008}. Ostrava: Faculty of Electrical Engineering and Computer Science, VŠB - Technical University of Ostrava, 2008, p.~72-80. ISBN~978-80-248-1875-7.
|
