Bayesian Reordering Model with Feature Selection

Abstract

In phrase-based statistical machine translation systems, variation in grammatical structures between source and target languages can cause large movements of phrases. Modeling such movements is crucial in achieving translations of long sentences that appear natural in the target language. We explore generative learning approach to phrase reordering in Arabic to English. Formulating the reordering problem as a classification problem and using naive Bayes with feature selection, we achieve an improvement in the BLEU score over a lexicalized reordering model. The proposed model is compact, fast and scalable to a large corpus.

Learning Better Classification-Based Reordering Model for Phrase-Based Translation

“…Among the lexicalized reordering models, Bracket Transduction Grammar (BTG) restriction is widely used for reordering in SMT (Zens et al, 2004) due to its good tradeoff between efficiency and expressiveness. Under framework of BTG, the reordering task is considered as classification problem and achieves good performance (Abdullah et al, 2014), referred to as the classification-based reordering model (CRM). The maximum entropy classifier is widely adopted by many researchers to implement the CRM (Zens and Ney, 2006;Xiong et al, 2006;Nguyen et al, 2009;Xiang et al, 2011), and is also considered in this work.…”