KRÁL, Robert. Word Sense Discrimination for Czech. In Text, Speech and Dialogue, 5th International Conference TSD 2002. Berlin: Springer-Verlag, 2002, p. 155-158. ISBN 3-540-44129-8.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Word Sense Discrimination for Czech
Authors KRÁL, Robert (203 Czech Republic, guarantor).
Edition Berlin, Text, Speech and Dialogue, 5th International Conference TSD 2002, p. 155-158, 2002.
Publisher Springer-Verlag
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 20206 Computer hardware and architecture
Country of publisher Germany
Confidentiality degree is not subject to a state or trade secret
RIV identification code RIV/00216224:14330/02:00008560
Organization unit Faculty of Informatics
ISBN 3-540-44129-8
Keywords in English natural language processing; word sense disambiguation; clustering; Czech language
Tags clustering, Czech language, natural language processing, word sense disambiguation
Changed by Changed by: Mgr. BcA. Robert Král, Ph.D., učo 3960. Changed: 25/9/2003 09:55.
Abstract
This paper deals with the automatic discrimination of contexts of Czech ambiguous words. The Schutze's methodology was used, modified and transformed for the Czech language. This algorithm is based on vector space and clustering. The semantic discrimination could be understood as a subtask of word sense disambiguation. In this approach, the sense of word is defined as the cluster of contexts of ambiguous word. We show that Schutze's method is transportable into Czech. Our results are not as good as his because we have experimented with a highly ambiguous word.
Links
MSM 143300003, plan (intention)Name: Interakce člověka s počítačem, dialogové systémy a asistivní technologie
Investor: Ministry of Education, Youth and Sports of the CR, Human-computer interaction, dialog systems and assistive technologies
PrintDisplayed: 27/4/2024 04:44