tailieunhanh - Báo cáo khoa học: "A Localized Prediction Model for Statistical Machine Translation"

In this paper, we present a block-based model for statistical machine translation. A block is a pair of phrases which are translations of each other. For example, Fig. 1 shows an Arabic-English translation example that uses blocks. During decoding, we view translation as a block segmentation process, where the input sentence is segmented from left to right and the target sentence is generated from bottom to top, one block at a time. A monotone block sequence is generated except for the possibility to swap a pair of neighbor blocks. We use an orientation model similar to the lexicalized block. | A Localized Prediction Model for Statistical Machine Translation Christoph Tillmann and Tong Zhang IBM TJ. Watson Research Center Yorktown Heights NY 10598 USA ctill tzhang @ Abstract In this paper we present a novel training method for a localized phrase-based prediction model for statistical machine translation SMT . The model predicts blocks with orientation to handle local phrase re-ordering. We use a maximum likelihood criterion to train a log-linear block bigram model which uses realvalued features . a language model score as well as binary features based on the block identities themselves . block bigram features. Our training algorithm can easily handle millions of features. The best system obtains a improvement over the baseline on a standard Arabic-English translation task. aữspa Lebanese vlolale warplanes Israeli A 1 A 1 A 1 Ì n A 1 A Ị A 1 T H A t m j 1 Ặ r s h j w b b r k A y n r y A 1 A A p n t y y 1 Introduction In this paper we present a block-based model for statistical machine translation. A block is a pair of phrases which are translations of each other. For example Fig. 1 shows an Arabic-English translation example that uses 4 blocks. During decoding we view translation as a block segmentation process where the input sentence is segmented from left to right and the target sentence is generated from bottom to top one block at a time. A monotone block sequence is generated except for the possibility to swap a pair of neighbor blocks. We use an orientation model similar to the lexicalized block re-ordering model in Tillmann 2004 Och et al. 2004 to generate a block b with orientation Ỡ relative to its predecessor block 6 . During decoding we compute the probability p b o of a block sequence 6 with orientation o as a product of block bigram probabilities 011 -1 01-1 1 i l y p Figure 1 An Arabic-English block translation example where the Arabic words are romanized. The following orientation sequence is generated 01 N 02 L o3 N Ỡ4