2026-04-13T07:36:25Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/112712025-07-17T08:16:29Zcom_2072_1033col_2072_452950

Using linear interpolation and weighted reordering hypotheses in the moses system Ruiz Costa-Jussà, Marta Rodríguez Fonollosa, José Adrián Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions Universitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla Àrees temàtiques de la UPC::Enginyeria de la telecomunicació Statistical machine translation Machine translation Signal theory (Telecommunication) Speech processing systems Senyal, Teoria del (Telecomunicació) Traducció automàtica 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. Postprint (published version) 2011 Conference lecture 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. 2-9517408-6-7 https://hdl.handle.net/2117/11271 eng http://www.lrec-conf.org/proceedings/lrec2010/pdf/23_Paper.pdf Open Access 7 p. application/pdf