tailieunhanh - Báo cáo khoa học: "A Joint Rule Selection Model for Hierarchical Phrase-based Translation"

In hierarchical phrase-based SMT systems, 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 simultaneously. This paper presents a joint model to predict the selection of hierarchical rules. | A Joint Rule Selection Model for Hierarchical Phrase-based Translation Lei Cui Dongdong Zhang Mu Li Ming Zhou and Tiejun Zhao School of Computer Science and Technology Harbin Institute of Technology Harbin China cuilei tjzhao @ Microsoft Research Asia Beijing China dozhang muli mingzhou @ Abstract In hierarchical phrase-based SMT systems 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 simultaneously. This paper presents a joint model to predict the selection of hierarchical rules. The proposed model is estimated 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 practical SMT systems with the log-linear model framework. The experimental results show that our method can yield significant improvements in performance. 1 Introduction Hierarchical phrase-based model has strong expression capabilities of translation knowledge. It can not only maintain the strength of phrase translation in traditional phrase-based models Koehn et al. 2003 Xiong et al. 2006 but also characterize the complicated long distance reordering similar to syntactic based statistical machine translation SMT models Yamada and Knight 2001 Quirk et al. 2005 Galley et al. 2006 Liu et al. 2006 Marcu et al. 2006 Mi et al. 2008 Shen et al. 2008 . In hierarchical phrase-based SMT systems due to the flexibility of rule matching a huge number of hierarchical rules could be automatically learnt from bilingual training corpus Chiang 2005 . SMT decoders are forced to face the challenge of This work was finished while the first author visited Microsoft Research Asia as an intern. proper rule selection for hypothesis generation including both .

TÀI LIỆU LIÊN QUAN
TỪ KHÓA LIÊN QUAN