Hierarchical Phrase-based Machine Translation with Word-based Reordering Model

Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 439–446, Beijing, August 2010 Hierarchical Phrase-based Machine Translation with Word-based Reordering Model Katsuhiko Hayashi*, Hajime Tsukada** Katsuhito Sudoh**, Kevin Duh**, Seiichi Yamamoto* *Doshisha University katsuhiko-h@is.naist.jp, seyamamo@mail.doshisha.ac.jp **NTT Communication Science Laboratories tsukada, sudoh, kevinduh@cslab.kecl.ntt.co.jp Abstract Hierarchical phrase-based machine trans- lation can capture global reordering with synchronous context-free grammar, but has little ability to evaluate the correctness of word orderings during decoding. We propose a method to integrate word-based reordering model into hierarchical phrase- based machine translation to overcome this weakness. Our approach extends the synchronous context-free grammar rules of hierarchical phrase-based model to in- clude reordered source strings, allowing efficient calculation of reordering model scores during decoding. Our experimen- tal results on Japanese-to-English basic travel expression corpus showed that the BLEU scores obtained by our proposed system were better than those obtained by a standard hierarchical phrase-based ma- chine translation system. 1 Introduction Hierarchical phrase-based machine translation (Chiang, 2007; Watanabe et al., 2006) is one of the promising statistical machine translation ap- proaches (Brown et al., 1993). Its model is for- mulated by a synchronous context-free grammar (SCFG) which captures the syntactic information between source and target languages. Although the model captures global reordering by SCFG, it does not explicitly introduce reordering model to constrain word order. In contrast, lexicalized reordering models (Tillman, 2004; Koehn et al., 2005; Nagata et al., 2006) are extensively used for phrase-based translation. These lexicalized re- ordering models cannot be directly applied to hi- erarchical phrased-based translation since the hi- erarchical phrase representation uses nonterminal symbols. To handle global reordering in phrase-based translation, various preprocessing approaches have been proposed, where the source sentence is reordered to target language order beforehand (Xia and McCord, 2004; Collins et al., 2005; Li et al., 2007; Tromble and Eisner, 2009). However, preprocessing approaches cannot utilize other in- formation in the translation model and target lan- guage model, which has been proven helpful in decoding. This paper proposes a method that incorpo- rates word-based reordering model into hierarchi- cal phrase-based translation to constrain word or- der. In this paper, we adopt the reordering model originally proposed by Tromble and Eisner (2009) for the preprocessing approach in phrase-based translation. To integrate the word-based reorder- ing model, we added a reordered source string into the right-hand-side of SCFG’s rules. By this extension, our system can generate the reordered source sentence as well as target sentence and is able to efficiently calculate the score of the re- ordering model. Our method utilizes the transla- tion model and target language model as well as the reordering model during decoding. This is an advantage of our method over the preprocessing approach. The remainder of this paper is organized as follows. Section 2 describes the concept of our approach. Section 3 briefly reviews our pro- posed method on hierarchical phrase-based ma- 439 Standard SCFG X →< X1 wa jinsei no X2 da , X1 is X2 of life> SCFG (move-to-front) X →< X1 wa jinsei …

Content truncated to 500 words