Maximum Entropy Based Phrase Reordering for Hierarchical Phrase-Based Translation

Hierarchical phrase-based (HPB) translation provides a powerful mechanism to capture both short and long distance phrase reorderings. However, the phrase reorderings lack of contextual information in conventional HPB systems. This paper proposes a contextdependent phrase reordering approach that uses the maximum entropy (MaxEnt) model to help the HPB decoder select appropriate reordering patterns. We classify translation rules into several reordering patterns, and build a MaxEnt model for each pattern based on various contextual features. We integrate the MaxEnt models into the HPB model. Experimental results show that our approach achieves significant improvements over a standard HPB system on large-scale translation tasks. On Chinese-to-English translation, the absolute improvements in BLEU (case

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Zhongjun He, Yao Meng, Hao Yu
• Keywords: Appropriate Reordering Patterns, Conventional Hpb Systems, EMNLP 2010, MaxEnt Models, Natural Language Processing