Improving Statistical Machine Translation with Processing Shallow Parsing

Copyright 2012 by Hoai-Thu Vuong, Vinh Van Nguyen, Viet Hong Tran, and Akira Shimazu 26th Pacific Asia Conference on Language,Information and Computation pages 401–407 Improving Statistical Machine Translation with Processing Shallow Parsing Hoai-Thu Vuong, Vinh Van Nguyen University of Engineering and Technology, Vietnam National University 144, Xuan Thuy, Cau Giay , Hanoi {thuvh, vinhnv}@vnu.edu.vn Viet Hong Tran Department of Information Technology University Of Economic And Technical Industries 456 Minh Khai, Hai Ba Trung, Hanoi thviet@uneti.edu.vn Akira Shimazu Japan Advanced Institute of Science and Technology 1-1, Asahidai, Nomi, Ishikawa, 923-1292, Japan shimazu@jaist.ac.jp Abstract Reordering is of essential importance for phrase based statistical machine translation (SMT). In this paper, we would like to present a new method of reordering in phrase based SMT. We inspired from (Xia and Mc- Cord, 2004) using preprocessing reorder- ing approaches. We used shallow pars- ing and transformation rules to reorder the source sentence. The experiment results from English-Vietnamese pair showed that our approach achieves significant improvements over MOSES which is the state-of-the art phrase based system. 1 Introduction In SMT, the reordering problem (global reordering) is one of the major problems, since different lan- guages have different word order requirements. The SMT task can be viewed as two subtasks: predicting the collection of words in a translation, and deciding the order of the predicted words (reordering prob- lem). Currently, phrase-based statistical machine translation (Koehn et al., 2003; Och and Ney, 2004) is the state-of-the-art of SMT because of its power in modelling short reordering and local context. However, with phrase based SMT, long distance reordering is still problematic. In order to tackle the long distance reordering problem, in recent years, huge research efforts have been conducted using syntactic information. There are some studies on integrating syntactic resources within SMT. Chiang (Chiang, 2005) shows significant improvement by keeping the strengths of phrases, while incorporat- ing syntax into SMT. Some approaches have been applied at the word-level (Collins et al., 2005). They are particularly useful for language with rich mor- phology, for reducing data sparseness. Other kinds of syntax reordering methods require parser trees , such as the work in (Quirk et al., 2005; Collins et al., 2005; Huang and Mi, 2010). The parsed tree is more powerful in capturing the sentence structure. However, it is expensive to create tree structure, and building a good quality parser is also a hard task. All the above approaches require much decoding time, which is expensive. The approach we are interested in here is to bal- ance the quality of translation with decoding time. Reordering approaches as a preprocessing step (Xia and McCord, 2004; Xu et al., 2009; Talbot et al., 2011; Katz-Brown et al., 2011) is very effective (im- provement significant over state of-the-art phrase- based and hierarchical machine translation systems and separately quality evaluation of reordering mod- els). Inspiring this preprocessing approach, we have proposed a combine approach which preserves the strength of phrase-based SMT in local reordering and decoding time as well as the strength of inte- grating …

Content truncated to 500 words