SOJKA, Petr. Towards the Realistic Natural Language Representations. In Seventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2013. Brno: Tribun EU, 2013. p. 87-91, 5 pp. ISBN 978-80-263-0520-0.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Towards the Realistic Natural Language Representations
Authors SOJKA, Petr (203 Czech Republic, guarantor, belonging to the institution).
Edition Brno, Seventh Workshop on Recent Advances in Slavonic Natural Language Processing, RASLAN 2013, p. 87-91, 5 pp. 2013.
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 preprint článku slides
RIV identification code RIV/00216224:14330/13:00070355
Organization unit Faculty of Informatics
ISBN 978-80-263-0520-0
Keywords (in Czech) reprezentace jazyka; výběr významu; výběr významového slova; výběr významu slova; diskretizace reprezentace; reprezentace významu; empirická lingvistika
Keywords in English natural language representation; priming; lexical priming; semantic priming; data discretization; language modelling; representation of meaning; personal mental lexicon; empirical linguistics
Tags International impact
Changed by Changed by: doc. RNDr. Petr Sojka, Ph.D., učo 2378. Changed: 9/12/2013 08:30.
This essay suggests a way to derive a natural language representation from textual corpora into the connectionist, continuous representations. Based on the lexical priming theory and psycholinguistic evidence we discuss benefits and potential of alternative representations inspired by connectionist approaches towards computation of personalized mental lexicon from and during empirical language usage.
250503, internal MU codeName: The European Digital Mathematics Library (Acronym: EuDML)
Investor: European Union, Competitiveness and inovation framework programme
PrintDisplayed: 29/3/2020 10:26