首页 | 官方网站   微博 | 高级检索  
     

层次短语翻译中基于Markov 随机场的层次切分模型
引用本文:刘乐茂,赵铁军,曹海龙,朱聪慧,张春越.层次短语翻译中基于Markov 随机场的层次切分模型[J].软件学报,2012,23(12):3088-3100.
作者姓名:刘乐茂  赵铁军  曹海龙  朱聪慧  张春越
作者单位:哈尔滨工业大学计算机科学与技术学院,黑龙江哈尔滨 150001;语言语音教育部-微软重点实验室(哈尔滨工业大学),黑龙江哈尔滨150001
基金项目:国家自然科学基金,国家高技术研究发展计划(863)
摘    要:翻译推导的切分歧义是统计机器翻译面临的一个很重要的问题,而在层次短语机器翻译中,其尤为突出.提出了一个层次切分模型来处理推导的切分歧义性.采用Markov随机场构建模型,然后将其融入层次短语翻译模型,以便自动选择更合理的切分.在NIST中英翻译的任务中,该模型的训练效率高,通过NIST05,NIST06和NIST08这3个测试集上的翻译效果表明,该模型提高了层次短语翻译的性能.

关 键 词:层次短语翻译  切分模型  图模型  Markov随机场  依存树
收稿时间:2011/7/14 0:00:00
修稿时间:2012/3/19 0:00:00

Hierarchical Partition Model Based on Markov Random Fields for Hierarchical Phrase- Based Machine Translation
LIU Le-Mao,ZHAO Tie-Jun,CAO Hai-Long,ZHU Cong-Hui and ZHANG Chun-Yue.Hierarchical Partition Model Based on Markov Random Fields for Hierarchical Phrase- Based Machine Translation[J].Journal of Software,2012,23(12):3088-3100.
Authors:LIU Le-Mao  ZHAO Tie-Jun  CAO Hai-Long  ZHU Cong-Hui and ZHANG Chun-Yue
Affiliation:1,2 1(School of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China) 2(MOE-MS Key Laboratory of Natural Language Processing and Speech(Harbin Institute of Technology),Harbin 150001,China)
Abstract:The partition ambiguity of translation derivations is an important problem suffered by the statistical machine translation, and it is much more important in a hierarchical phrase-based machine translation. In the paper, a hierarchical partition model is proposed to address the problem. The study applies markov random fields to construct the model, and integrate it into the hierarchical translation model to automatically select the more reasonable partition. In the NIST Chinese-English translation tasks, the optimization of the model is very efficient, and it improves the translation performance for hierarchical phrase-based translation on NIST05, NIST06 and NIST08 test sets.
Keywords:hierarchical phrase translation  partition model  graphical model  Markov random fields  dependency tree
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号