Paper: A Joint Rule Selection Model for Hierarchical Phrase-Based Translation

ACL ID P10-2002
Title A Joint Rule Selection Model for Hierarchical Phrase-Based Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2010
Authors

In hierarchical phrase-based SMT sys- tems, statistical models are integrated to guide the hierarchical rule selection for better translation performance. Previous work mainly focused on the selection of either the source side of a hierarchical rule or the target side of a hierarchical rule rather than considering both of them si- multaneously. This paper presents a joint model to predict the selection of hierar- chical rules. The proposed model is esti- mated based on four sub-models where the rich context knowledge from both source and target sides is leveraged. Our method can be easily incorporated into the prac- tical SMT systems with the log-linear model framework. The experimental re- sults show that our method can yield sig- nificant improvements in performance.