[ 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 2016
Type in proceedings
Status published
Language English
Author(s) Gaudio, Rosa Labaka, Gorka Agirre, Eneko Osenova, Petya Simov, Kiril Popel, Martin Oele, Dieke van Noord, Gertjan Gomes, Luís Rodrigues, João António Neale, Steven Silva, João Querido, Andreia Rendeiro, Nuno Branco, António
Title SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task
Czech title Statistické a hybridní systémy strojového překladu z projektu QTLeap v úloze IT překladu WMT16
Proceedings 2016: Stroudsburg, PA, USA: WMT 2016 (ACL): Proceedings of the First Conference on Machine Translation (WMT). Volume 2: Shared Task Papers
Pages range 435-441
How published online
URL http://www.statmt.org/wmt16/pdf/W16-2332.pdf
Supported by 2013-2016 FP7-ICT-2013-10-610516 (QTLeap) 2016 SVV 260 333 (Teoretické základy informatiky a výpočetní lingvistiky)
Czech abstract Tento článek představuje 12 systémů zaslaných do úlohy strojového překladu textů z IT domény v rámci WMT16. Systémy překládají z angličtiny do 6 jazyků: baskičtiny, bulharštiny, holandštiny, češtiny, portugalštiny a španělštiny. Všechny systémy byly vyvinuty v rámci projektu QTLeap. Pro každý jazykový pár byly zaslány dva systémy: frázový (Moses) a hloubkově-syntaktický (TectoMT, krom bulharštiny). Pro 4 z 6 jazyků dosáhlo TectoMT lepších výsledků než Moses.
English abstract This paper presents the description of 12 systems submitted to the WMT16 IT-task, covering six different languages, namely Basque, Bulgarian, Dutch, Czech, Portuguese and Spanish. All these systems were developed under the scope of the QTLeap project, presenting a common strategy. For each language two different systems were submitted, namely a phrase-based MT system built using Moses, and a system exploiting deep language engineering approaches, that in all the languages but Bulgarian was implemented using TectoMT. For 4 of the 6 languages, the TectoMT-based system performs better than the Moses-based one.
Specialization linguistics ("jazykověda")
Confidentiality default – not confidential
Open access no
Editor(s)* Ondřej Bojar; et al .
ISBN* 978-1-945626-10-4
Address* Stroudsburg, PA, USA
Month* August
Venue* Humboldt University
Publisher* Association for Computational Linguistics
Institution* Association for Computational Linguistics
Creator: Common Account
Created: 8/2/16 5:15 PM
Modifier: Almighty Admin
Modified: 2/25/17 10:07 PM
***

Content, Design & Functionality: ÚFAL, 2006–2016. Page generated: Sun Sep 24 00:07:16 CEST 2017

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

100% OpenAIRE compliant