Czech-English Phrase-Based Machine Translation.pdf

Czech-English Phrase-Based Machine Translation Ondr?ej Bojar1, Evgeny Matusov2, and Hermann Ney2 1 Institute of Formal and Applied Linguistics
U?FAL MFF UK, Malostranske? na?me?st?? 25, CZ-11800 Praha, Czech Republic bojar@ufal.mff.cuni.cz 2 Lehrstuhl fu?r Informatik 6, Computer Science Department RWTH Aachen University, D-52056 Aachen, Germany {matusov, ney}@cs.rwth-aachen.de Abstract. Wedescribe experiments with Czech-to-English phrase-based machine translation. Several techniques for improving translation quality (in terms of well-established measure BLEU) are evaluated. In total, we are able to achieve BLEU of 0.36 to 0.41 on the examined corpus of Wall Street Journal texts, outperforming all other systems evaluated on this language pair. 1 Introduction We aim at Czech-to-English machine translation (MT). For the time being, top performing systems of machine translation are statistical and phrase-based.1 Czech is a thoroughly studied Slavonic language with extensive language data resources available (most notably the Prague Dependency Treebank, PDT2, [1]). Czech is an inflective language with rich morphology and relatively free word order allowing non-projective constructions. These properties usually cast some doubt on the applicability of “uninformed” statistical methods that do not at- tempt at analyzing sentence structure. Traditionally, most of the research on Czech is performed within the frame- work of the Functional Generative Description (FGD, [2]), a dependency-based formalism defining the deep syntactic (syntactico-semantic) level of language de- scription. Effort has been invested in the development of linguistically adequate annotated data (PDT and lexicons) and tools (taggers, parsers to surface and deep syntactic levels, see the PDT for references). MT is attempted at the deep syntactic level [3]. In this paper, we describe our experiments with a phrase-based statistical MT system (PBT) developed at RWTH Aachen University [4]. We observe that at