Mostra el registre d'ítem simple
Using linear interpolation and weighted reordering hypotheses in the moses system
dc.contributor.author | Ruiz Costa-Jussà, Marta |
dc.contributor.author | Rodríguez Fonollosa, José Adrián |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions |
dc.date.accessioned | 2011-02-02T17:32:06Z |
dc.date.available | 2011-02-02T17:32:06Z |
dc.date.created | 2011 |
dc.date.issued | 2011 |
dc.identifier.citation | Costa-Jussà, M. R.; Fonollosa, José A. R. Using linear interpolation and weighted reordering hypotheses in the moses system. A: International Conference on Language Resources and Evaluation. "Seventh Conference on International Language Resources and Evaluation". Valletta: 2011, p. 1712-1718. |
dc.identifier.isbn | 2-9517408-6-7 |
dc.identifier.uri | http://hdl.handle.net/2117/11271 |
dc.description.abstract | This paper proposes to introduce a novel reordering model in the open-source Moses toolkit. The main idea is to provide weighted reordering hypotheses to the SMT decoder. These hypotheses are built using a first-step Ngram-based SMT translation from a source language into a third representation that is called reordered source language. Each hypothesis has its own weight provided by the Ngram-based decoder. This proposed reordering technique offers a better and more efficient translation when compared to both the distance-based and the lexicalized reordering. In addition to this reordering approach, this paper describes a domain adaptation technique which is based on a linear combination of an specific indomain and an extra out-domain translation models. Results for both approaches are reported in the Arabic-to-English 2008 IWSLT task. When implementing the weighted reordering hypotheses and the domain adaptation technique in the final translation system, translation results reach improvements up to 2.5 BLEU compared to a standard state-of-the-art Moses baseline system. |
dc.format.extent | 7 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Enginyeria de la telecomunicació |
dc.subject.lcsh | Statistical machine translation |
dc.subject.lcsh | Machine translation |
dc.subject.lcsh | Signal theory (Telecommunication) |
dc.subject.lcsh | Speech processing systems |
dc.title | Using linear interpolation and weighted reordering hypotheses in the moses system |
dc.type | Conference lecture |
dc.subject.lemac | Senyal, Teoria del (Telecomunicació) |
dc.subject.lemac | Traducció automàtica |
dc.contributor.group | Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla |
dc.relation.publisherversion | http://www.lrec-conf.org/proceedings/lrec2010/pdf/23_Paper.pdf |
dc.rights.access | Open Access |
local.identifier.drac | 4928146 |
dc.description.version | Postprint (published version) |
local.citation.author | Costa-Jussà, M. R.; Fonollosa, José A. R. |
local.citation.contributor | International Conference on Language Resources and Evaluation |
local.citation.pubplace | Valletta |
local.citation.publicationName | Seventh Conference on International Language Resources and Evaluation |
local.citation.startingPage | 1712 |
local.citation.endingPage | 1718 |