首页 | 本学科首页   官方微博 | 高级检索  
     

基于树形条件随机场的跨语言时态标注
引用本文:陈怡疆,徐海波,史晓东,苏畅.基于树形条件随机场的跨语言时态标注[J].软件学报,2015,26(12):3151-3161.
作者姓名:陈怡疆  徐海波  史晓东  苏畅
作者单位:厦门大学计算机科学系, 福建 厦门 361005,厦门大学计算机科学系, 福建 厦门 361005,厦门大学智能科学与技术系, 福建 厦门 361005,厦门大学智能科学与技术系, 福建 厦门 361005
基金项目:国家自然科学基金(61075058);国家科技支撑计划(2012BAH14F03)
摘    要:提出时态树的概念和构造方法,从而将汉英时态转换问题转换为时态树标注的问题.而后,使用树形条件随机场为未标注时态树的结点标注英语时态.提出的特征函数的模板较好地满足了模型推断的需要.实验结果表明:与基于线性条件随机场模型的时态标注方法相比,基于时态树方法的准确率有大幅度的提高,说明使用时态树能够更好地表达子句间时态的依赖关系.

关 键 词:汉英时态转换  时态树  未标注时态树  已标注时态树  树形条件随机场
收稿时间:2014/3/23 0:00:00
修稿时间:2014/8/27 0:00:00

Cross-Lingual Tense Tagging Based on Tree Conditional Random Fields
CHEN Yi-Jiang,XU Hai-Bo,SHI Xiao-Dong and SU Chang.Cross-Lingual Tense Tagging Based on Tree Conditional Random Fields[J].Journal of Software,2015,26(12):3151-3161.
Authors:CHEN Yi-Jiang  XU Hai-Bo  SHI Xiao-Dong and SU Chang
Affiliation:Department of Computer Science, Xiamen University, Xiamen 361005, China,Department of Computer Science, Xiamen University, Xiamen 361005, China,Department of Cognitive Science, Xiamen University, Xiamen 361005, China and Department of Cognitive Science, Xiamen University, Xiamen 361005, China
Abstract:In this paper, the concept of a tense tree and its construction method are proposed such that the issue of Chinese-English tense conversion is transformed into the issue of tagging a tense tree. Futher, tree-CRF is used to tag nodes of the untagged tense tree with English tenses. Templates of feature functions are suitable for the need of model inference. Experimental results show that the method of tree-based tense tagging is much better than linear-based tense tagging, and that tense trees can better express tense dependencies between clauses.
Keywords:Chinese-English tense conversion  tense tree  untagged tense tree  tagged tense tree  tree-CRF
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