- -

Online learning via dynamic reranking for Computer Assisted Translation

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

Online learning via dynamic reranking for Computer Assisted Translation

Show simple item record

Files in this item

dc.contributor.author Martínez Gómez, Pascual es_ES
dc.contributor.author Sanchis Trilles, Germán es_ES
dc.contributor.author Casacuberta Nolla, Francisco es_ES
dc.date.accessioned 2014-05-06T07:26:02Z
dc.date.issued 2011
dc.identifier.isbn 978-3-642-19436-8
dc.identifier.issn 0302-9743
dc.identifier.uri http://hdl.handle.net/10251/37239
dc.description.abstract New techniques for online adaptation in computer assisted translation are explored and compared to previously existing approaches. Under the online adaptation paradigm, the translation system needs to adapt itself to real-world changing scenarios, where training and tuning may only take place once, when the system is set-up for the first time. For this purpose, post-edit information, as described by a given quality measure, is used as valuable feedback within a dynamic reranking algorithm. Two possible approaches are presented and evaluated. The first one relies on the well-known perceptron algorithm, whereas the second one is a novel approach using the Ridge regression in order to compute the optimum scaling factors within a state-of-the-art SMT system. Experimental results show that such algorithms are able to improve translation quality by learning from the errors produced by the system on a sentence-by-sentence basis. es_ES
dc.description.sponsorship This paper is based upon work supported by the EC (FEDER/FSE) and the Spanish MICINN under projects MIPRCV “Consolider Ingenio 2010” (CSD2007-00018) and iTrans2 (TIN2009-14511). Also supported by the Spanish MITyC under the erudito.com (TSI-020110-2009-439) project, by the Generalitat Valenciana under grant Prometeo/2009/014 and scholarship GV/2010/067 and by the UPV under grant 20091027
dc.format.extent 13 es_ES
dc.language Inglés es_ES
dc.publisher Springer Verlag (Germany) es_ES
dc.relation MICINN/CSD2007-00018 es_ES
dc.relation MITyC/TSI-020110-2009-439 es_ES
dc.relation GV/Prometeo/2009/014 es_ES
dc.relation UPV/20091027 es_ES
dc.relation GV/2010/067
dc.relation MICINN/TIN2009-14511
dc.relation.ispartof Computational Linguistics and Intelligent Text Processing es_ES
dc.relation.ispartofseries Lecture Notes in Computer Science;6609
dc.rights Reserva de todos los derechos es_ES
dc.subject Machine Traslation es_ES
dc.subject.classification LENGUAJES Y SISTEMAS INFORMATICOS es_ES
dc.title Online learning via dynamic reranking for Computer Assisted Translation es_ES
dc.type Capítulo de libro es_ES
dc.embargo.lift 10000-01-01
dc.embargo.terms forever es_ES
dc.identifier.doi 10.1007/978-3-642-19437-5_8
dc.rights.accessRights Abierto es_ES
dc.contributor.affiliation Universitat Politècnica de València. Departamento de Sistemas Informáticos y Computación - Departament de Sistemes Informàtics i Computació es_ES
dc.contributor.affiliation Universitat Politècnica de València. Instituto Universitario Mixto Tecnológico de Informática - Institut Universitari Mixt Tecnològic d'Informàtica es_ES
dc.description.bibliographicCitation Martínez Gómez, P.; Sanchis Trilles, G.; Casacuberta Nolla, F. (2011). Online learning via dynamic reranking for Computer Assisted Translation. En » Computational Linguistics and Intelligent Text Processing. Springer Verlag (Germany). 6609:93-105. doi:10.1007/978-3-642-19437-5_8 es_ES
dc.description.accrualMethod Senia es_ES
dc.relation.conferencename 12th International Conference, CICLing 2011 es_ES
dc.relation.conferencedate February 20-26, 2011 es_ES
dc.relation.conferenceplace Tokyo, Japan es_ES
dc.relation.publisherversion http://link.springer.com/chapter/10.1007/978-3-642-19437-5_8 es_ES
dc.description.upvformatpinicio 93 es_ES
dc.description.upvformatpfin 105 es_ES
dc.type.version info:eu repo/semantics/publishedVersion es_ES
dc.description.volume 6609 es_ES
dc.relation.senia 210922
dc.contributor.funder Universitat Politècnica de València (UPV)
dc.contributor.funder Generalitat Valenciana (GV)
dc.contributor.funder Ministerio de Ciencia e Innovación (MICINN)


This item appears in the following Collection(s)

Show simple item record