A tree-based approach for English-to-Turkish translation

Abstract

In this paper, we present our English-to-Turkish translation methodology, which adopts a tree-basedapproach. Our approach relies on tree analysis and the application of structural modification rules to get the target side(Turkish) trees from source side (English) ones. We also use morphological analysis to get candidate root words and applytree-based rules to obtain the agglutinated target words. Compared to earlier work on English-to-Turkish translationusing phrase-based models, we have been able to obtain higher BLEU scores in our current study. Our syntactic subtreepermutation strategy, combined with a word replacement algorithm, provides a 67% relative improvement from a baseline12.8 to 21.4 BLEU, all averaged over 10-fold cross-validation. As future work, improvements in choosing the correctsenses and structural rules are needed.