Chinese Syntactic Reordering for Statistical Machine Translation

Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 737–745, Prague, June 2007. c⃝2007 Association for Computational Linguistics Chinese Syntactic Reordering for Statistical Machine Translation Chao Wang MIT CSAIL 32 Vassar Street, Room 362 Cambridge, MA 02139, USA wangc@csail.mit.edu Michael Collins MIT CSAIL 32 Vassar Street, Room G-484 Cambridge, MA 02139, USA mcollins@csail.mit.edu Philipp Koehn School of Informatics 2 Buccleuch Place, 5BP 2L2 Edinburgh, EH8 9LW, UK pkoehn@inf.ed.ac.uk Abstract Syntactic reordering approaches are an ef- fective method for handling word-order dif- ferences between source and target lan- guages in statistical machine translation (SMT) systems. This paper introduces a re- ordering approach for translation from Chi- nese to English. We describe a set of syntac- tic reordering rules that exploit systematic differences between Chinese and English word order. The resulting system is used as a preprocessor for both training and test sentences, transforming Chinese sentences to be much closer to English in terms of their word order. We evaluated the reordering approach within the MOSES phrase-based SMT system (Koehn et al., 2007). The reordering approach improved the BLEU score for the MOSES system from 28.52 to 30.86 on the NIST 2006 evaluation data. We also conducted a series of experiments to an- alyze the accuracy and impact of different types of reordering rules. 1 Introduction Syntactic reordering approaches are an effective method for handling systematic differences in word order between source and target languages within the context of statistical machine translation (SMT) systems (Xia and McCord, 2004; Collins et al., 2005). In reordering approaches, sentences in the source language are first parsed, for example using a Treebank-trained parser. A series of transformations is then applied to the resulting parse tree, with the goal of transforming the source language sentence into a word order that is closer to that of the target language. The reordering process is used to prepro- cess both the training and test data used within an existing SMT system. Reordering approaches have given significant improvements in performance for translation from French to English (Xia and Mc- Cord, 2004) and from German to English (Collins et al., 2005). This paper describes a syntactic reordering ap- proach for translation from Chinese to English. Fig- ure 1 gives an example illustrating some of the dif- ferences in word order between the two languages. The example shows a Chinese sentence whose literal translation in English is: this is French delegation at Winter Olympics on achieve DEC best accom- plishment and where a natural translation would be this is the best accomplishment that the French delegation achieved at the Winter Olympics As exemplified by this sentence, Chinese differs from English in several important respects: for ex- ample, relative clauses appear before the noun being modified; prepositional phrases often appear before the head they modify; and so on. It can be seen that some significant reordering of the input is required to produce a good English translation. For this ex- ample, application of reordering …

Content truncated to 500 words