首页 | 本学科首页   官方微博 | 高级检索  
     检索      

融合特征约束模型的纳西-汉语双语词语对齐算法
引用本文:张涛,余正涛,郭剑毅,曹先彬.融合特征约束模型的纳西-汉语双语词语对齐算法[J].西安交通大学学报,2011,45(10):48-53.
作者姓名:张涛  余正涛  郭剑毅  曹先彬
作者单位:1. 昆明理工大学信息工程与自动化学院,650051,昆明
2. 昆明理工大学信息工程与自动化学院,650051,昆明;昆明理工大学智能信息处理重点实验室,650051,昆明
3. 北京航空航天大学电子信息工程学院,100191,北京
基金项目:国家自然科学基金资助项目(60863011); 云南自然科学基金重点资助项目(2008CC023)
摘    要:针对纳西语、汉语因句法结构差异较大而导致双语词语自动对齐较为困难的问题,提出一种融合特征约束模型的纳西-汉语双语词语对齐算法.首先在语料中统计纳西-汉语词语区间扭曲和位置转换特性,并由此建立2个双语词语对齐的特征约束模型;然后将提出的特征约束模型融入词语对齐的对数线性模型框架,并结合最小错误率算法训练模型参数;最终搜索出最佳的词语对齐结果.实验以IBM Model3为词语对齐比较模型,结果表明,该双语词语对齐算法可以使纳西-汉语词语的对齐准确率提升21.9%.

关 键 词:词语对齐  纳西  汉语  特征约束模型

A Bilingual Word Alignment Algorithm of Naxi-Chinese Based on Feature Constraint Models
ZHANG Tao,YU Zhengtao,GUO Jianyi,CAO Xianbin.A Bilingual Word Alignment Algorithm of Naxi-Chinese Based on Feature Constraint Models[J].Journal of Xi'an Jiaotong University,2011,45(10):48-53.
Authors:ZHANG Tao  YU Zhengtao  GUO Jianyi  CAO Xianbin
Institution:ZHANG Tao~1,YU Zhengtao~(1,2),GUO Jianyi~(1,CAO Xianbin~3 (1.The School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650051,China,2.The Key Laboratory of Intelligent Information Processing,3.School of Electronics and Information Engineering,Beijing University of Aeronautics and Astronautics,Beijing 100191,China)
Abstract:A bilingual word alignment algorithm of Naxi-Chinese based on feature constraint models is proposed to reduce the difficulty of bilingual word alignment for Naxi-Chinese which has huge difference in syntactic structure.Two feature constraint models- interval distortion model and position transformation model are established by counting the traits of interval distortion and position transformation in corpus,and are integrated into a log-linear framework of word alignment. Then parameters in the models are tr...
Keywords:word alignment  Naxi  Chinese  feature constraint model  
本文献已被 CNKI 万方数据 等数据库收录!
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