[ Skip to the content ]

Institute of Formal and Applied Linguistics

at Faculty of Mathematics and Physics, Charles University, Prague, Czech Republic


[ Back to the navigation ]

Publication


Year 2013
Type in proceedings
Status published
Language English
Author(s) Bílek, Karel Klyueva, Natalia Kuboň, Vladislav
Title Exploiting Maching Learning for Automatic Semantic Feature Assignment
Czech title Využití strojového učení pro automatické přiřazování sémantických rysů
Proceedings 2013: Palo Alto, California: FLAIRS 26: Proceedings of the Twenty-Sixth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2013
Pages range 297-302
How published print
Supported by 2012-2013 GAUK 639012/2012 (Nástroje a data pro strojový překlad mezi blízkými jazyky) 2010-2013 GAP406/10/0875 (Komputační lingvistika: Explicitní popis jazyka a anotovaná data se zřetelem na češtinu) 2012-2016 PRVOUK P46 (Informatika)
Czech abstract Článek popisuje experimenty s přiřazováníém sémantických kategorií českým podstatným jménům pomocí metod strojového učení.
English abstract In this paper we experiment with supervised machine learning techniques for the task of assigning semantic categories to nouns in Czech. The experiments work with 16 semantic categories based on available manually annotated data. The paper compares two possible approaches - one based on the contextual information, the other based upon morphological properties - we are trying to automatically extract final segments of lemmas which might carry semantic information. The central problem of this research is finding the features for machine learning that produce better results for relatively small training data size.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
Editor(s)* Chutima Boonthum-Denecke; Michael G. Youngblood
ISBN* 978-1-57735-605-9
Address* Palo Alto, California
Month* May
Publisher* AAAI Press
Institution* FLAIRS
Creator: Common Account
Created: 11/7/13 4:22 PM
Modifier: Almighty Admin
Modified: 2/26/14 12:22 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Sun Nov 18 07:55:16 CET 2018

[ Back to the navigation ] [ Back to the content ]

100% OpenAIRE compliant