N-gram-based SMT system enhanced with reordering patterns
Josep Crego, Marta R. Costa‐jussà, José Bernardo Mariño Acebal, Adrià de Gispert, Maxim Khalilov, José A. R. Fonollosa, Patrik Lambert, Rafael E. Banchs · 2006
This work presents translation results for the three data sets made available in the shared task "Exploiting Parallel Texts for Statistical Machine Translation" of the HLT-NAACL 2006 Workshop on Statistical Machine Translation. All results presented were generated by using the N-gram-based statistical machine translation system which has been enhanced from the last year's evaluation with a tagged target language model (using Part-Of-Speech tags). For both Spanish-English translation directions and the English-to-French translation task, the baseline system allows for linguistically motivated source-side reorderings.