基于规则和实例相结合的英藏机器翻译系统的设计模型  

A Regulation and corpus-based English to Tibetan Machine translation system Design Model

作　　者：索南当周[1] 玛乃措[1] 曹玉林[1] 

机构地区：[1]西北工业大学

出　　处：《术语标准化与信息技术》2004年第4期37-42,共6页Terminology Standardization & Information Technology

摘　　要：当今社会处于Internet迅猛发展的信息时代,因此,迫切需要通过机器翻译来消除不同民族之间的文字沟通障碍。本文提出了一个基于规则和语料的英藏机器翻译系统的设计模型,概括介绍本系统的设计思想、设计原则,在选择翻译方法的基础上,着重阐述了系统的总体结构、翻译算法及语言模型,最后给出了进一步的设想。Now days, in the Internet swiftly developing Information Age. We really more depend on exchanging information based on it, the main issue is that there is some obstacle between different languages. So, we need a machine translation to eliminate the obstacle between different languages urgently. The paper gives a regulation and corpus -based machine translation system design model, discusses the design method and principle. On choosing translation method, the paper elaborates the overall structure, translation algorithm and linguistic model, and then gives a further study to the design model.

关 键 词：基于规则 机器翻译系统 设计模型 语言模型 算法 文字 实例 翻译方法 语料 概括 

分 类 号：TB47[一般工业技术—工业设计] TP311.11[自动化与计算机技术—计算机软件与理论]