MATERNA, Jiří and Juraj HREŠKO. A Bayesian Approach to Query Language Identification. In Aleš Horák, Pavel Rychlý. Recent Advances in Slavonic Natural Language Processing. Brno, Czech Republic: Tribun EU. p. 111-116, 137 pp. ISBN 978-80-263-0077-9. 2011.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name A Bayesian Approach to Query Language Identification
Name in Czech Bayesovský přístup k detekci jazyka dotazu
Authors MATERNA, Jiří (203 Czech Republic, guarantor, belonging to the institution) and Juraj HREŠKO (703 Slovakia, belonging to the institution).
Edition Brno, Czech Republic, Recent Advances in Slavonic Natural Language Processing, p. 111-116, 137 pp. 2011.
Publisher Tribun EU
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10201 Computer sciences, information science, bioinformatics
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
Publication form printed version "print"
WWW URL
RIV identification code RIV/00216224:14330/11:00054043
Organization unit Faculty of Informatics
ISBN 978-80-263-0077-9
Keywords (in Czech) detekce jazyka; jazyk dotazu; fulltextové vyhledávání
Keywords in English language identification; query language; information retrieval
Tags best3
Changed by Changed by: RNDr. Jiří Materna, Ph.D., učo 98897. Changed: 28/5/2021 12:04.
Abstract
In this paper we present a Bayesian approach to language identification of queries sent to an information retrieval system. The aim of the work is to identify both the language of a query as a whole and the language of particular words in the query. The method is evaluated on a test set of manually labelled queries. The evaluation shows that our method performs better than the Google Language Detect API and an implementation of the n-gram method on our testing set of queries.
Abstract (in Czech)
V tomoto článku představujeme Bayesovský přístup k detekci jazyka dotazů, zaslaných fulltextovému vyhledávači. Cílem práce je identifikovat jak jazyk dotazu jako celku, tak i jazyk jednotlivých slov dotazu. Metoda byla vyhodnocena na množině manuálně označkovaných dotazů. Ukázalo se, že naše metoda na dané testovací množině překonala kvalitu n-gramové metody i implementace Google Language Detect API.
Links
LC536, research and development projectName: Centrum komputační lingvistiky
Investor: Ministry of Education, Youth and Sports of the CR, Centrum komputační lingvistiky
PrintDisplayed: 19/4/2024 06:51