首页 | 本学科首页   官方微博 | 高级检索  
     

基于语义单元表示树剪枝的高速多语言机器翻译
引用本文:高小宇,高庆狮,胡玥,李莉.基于语义单元表示树剪枝的高速多语言机器翻译[J].软件学报,2005,16(11):1909-1919.
作者姓名:高小宇  高庆狮  胡玥  李莉
作者单位:中国科学院,计算技术研究所,北京,100080;中国科学院,计算技术研究所,北京,100080;北京科技大学,智能、语言与计算机科学研究所,北京,100083;北京科技大学,智能、语言与计算机科学研究所,北京,100083
基金项目:Supported by the National Natural Science Foundation of China under Grant No.60343010(国家自然科学基金);the Foundation of Institute of Computing Technology,the Chinese Academy of Sciences under Grant No.20016250(中国科学院计算技术研究所创新基金)
摘    要:提出一种基于语义单元表示树剪枝的高速多语言机器翻译方法.此方法是一种将汉语翻译到其他语种不需要先进行汉语切分的多语言机器翻译方法.而且翻译时间为O(L)而不是O(LN),其中,L是文本的长度,N是语义单元库中语义单元的数量,一般有数十万或者数百万.

关 键 词:自然语言  机器翻译  语义单元  语义单元表示  语义语言
文章编号:1000-9825/2005/16(11)1909
收稿时间:08 10 2004 12:00AM
修稿时间:2/3/2005 12:00:00 AM

High Speed Multi-Language Machine Translation Based on Pruning on the Tree of Representations of Semantic Elements
GAO Xiao-Yu,GAO Qing-Shi,HU Yue and LI Li.High Speed Multi-Language Machine Translation Based on Pruning on the Tree of Representations of Semantic Elements[J].Journal of Software,2005,16(11):1909-1919.
Authors:GAO Xiao-Yu  GAO Qing-Shi  HU Yue and LI Li
Affiliation:1.Institute of Computing Technology, The Chinese Academy of Sciences, Beijing 100080, China; 2.Institute of Intelligence, Linguistics and Computer Science, University of Science and Technology, Beijing 100083, China
Abstract:In this paper, a high speed multi-language machine translation approach based on pruning on tree representations of semantic elements is proposed. This is the multi-language machine translation with the following several characteristics: Chinese segmentation before translation into another languages is not necessary, and the translation time is O(L) rather than general O(LN), where L is the length of text, N is the number of semantic elements (i.e. number of language patterns) in SER-base, even if N is hundreds of thousands or millions.
Keywords:natural language  machine translation  semantic element  representation of semantic element  semantic language
本文献已被 CNKI 维普 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