Using linear interpolation and weighted reordering hypotheses in the moses system
Visualitza/Obre
Tipus de documentComunicació de congrés
Data publicació2011
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
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.
CitacióCosta-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.
ISBN2-9517408-6-7
Versió de l'editorhttp://www.lrec-conf.org/proceedings/lrec2010/pdf/23_Paper.pdf
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
LREC2010_Marta_Linear.pdf | 557,4Kb | Visualitza/Obre |