[ 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 2012
Type in proceedings
Status published
Language English
Author(s) Mareček, David Žabokrtský, Zdeněk
Title Unsupervised Dependency Parsing using Reducibility and Fertility features
Czech title Neřízený závislostní parsing využívající vlastnost vypustitelnosti a fertility
Proceedings 2012: Montréal, Canada: WILS 2012: The NAACL-HLT Workshop on the Induction of Linguistic Structure
Pages range 84-89
Supported by 2010-2013 FP7-ICT-2009-4-247762 (Faust) 2011-2013 7E11041 (Feedback Analysis for User Adaptive Statistical Translation) 2009-2012 GD201/09/H057 (Res Informatica) 2010-2012 GAUK 116310/2010 (Anglicko-český strojový překlad s využitím hloubkové syntaxe) 2012-2016 PRVOUK P46 (Informatika)
Czech abstract This paper describes a system for unsuper- vised dependency parsing based on Gibbs sampling algorithm. The novel approach in- troduces a fertility model and reducibility model, which assumes that dependent words can be removed from a sentence without vio- lating its syntactic correctness.
English abstract Popis systemu nerizeneho zavislostniho parsingu zalozeneho na Gibbsove samplingu. Novy pristup predstavuje vlastnosti vypusttelnsti a fertility.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
ISBN* 978-1-937284-20-6
Address* Montréal, Canada
Month* June
Publisher* The Association for Computational Linguistics
Organization* The Association for Computational Linguistics
Creator: Common Account
Created: 6/24/12 11:44 AM
Modifier: Almighty Admin
Modified: 9/6/13 4:51 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Mon Oct 15 18:26:49 CEST 2018

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

100% OpenAIRE compliant