Graph-based Lexicalized Reordering Models for Statistical Machine Translation

作     者：SU Jinsong LIU Yang LIU Qun DONG Huailin SU Jinsong;LIU Yang;LIU Qun;DONG Huailin;Xiamen University;Tsinghua University;Institute of Computing Technology,Chinese Academy of Sciences

作者机构：Xiamen University Xiamen 361005 E R. China Tsinghua University Beijing 100084 P. R. China Institute of Computing Technology Chinese Academy of Sciences Beijing 100084 P. R. China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2014年第11卷第5期

页      面：71-82页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081203[工学-计算机应用技术] 08[工学] 070105[理学-运筹学与控制论] 0835[工学-软件工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.61303082) the Research Fund for the Doctoral Program of Higher Education of China(No.20120121120046) 

主　　题：natural language processing statistical machine translation lexicalized reordering model reordering graph 

摘      要：Lexicalized reordering models are very important components of phrasebased translation *** examining the reordering relationships between adjacent phrases,conventional methods learn these models from the word aligned bilingual corpus,while ignoring the effect of the number of adjacent bilingual *** this paper,we propose a method to take the number of adjacent phrases into account for better estimation of reordering *** of just checking whether there is one phrase adjacent to a given phrase,our method firstly uses a compact structure named reordering graph to represent all phrase segmentations of a parallel sentence,then the effect of the adjacent phrase number can be quantified in a forward-backward fashion,and finally incorporated into the estimation of reordering *** results on the NIST Chinese-English and WMT French-Spanish data sets show that our approach significantly outperforms the baseline method.