【作者】 易绵竹； 薛恩奎； 李绍哲； 南振兴；

【Author】 Yi Mianzhu Xue Enkui Li Shaozhe Nan ZhenxingCenter for Russian Language and Literat Studies of Heilongjiang University,Harbin 150080, ChinaInstitute of Language and Culture Studies for National Defence, PLA University of Foreign Languages, Luoyang 471003, China

【机构】 黑龙江大学俄语语言文学研究中心； 解放军外国语学院国防语言文化研究所；

【摘要】 在本文我们将扼要介绍由俄罗斯科学院信息传输问题研究所计算语言学实验室研制的机器翻译系统ETAP-3,它由一个机器翻译系统、与SQL型数据库的自然语言接口、同义转换模块、句法纠错模块和计算机辅助语言学习工具等几种应用软件组成。本文的重点是描述一个旨在与联合国大学开发的通用网络语言(UNL)接口的信息处理新模块,嵌入在ETAP-3系统中的UNL模块采用机器翻译中广为接受的两种主要方法:基于转换的方法和中介语方法。更多还原

【Abstract】 In this paper, we shall briefly introduce to the translation system ETAP-3 developing by Laboratory of Computational Linguistics of Institute for Information Transmission Problems, Russian Academy of Sciences. As a multifunctional NLP environment, the ETAP-3 has several NLP applications, including a machine translation system, a natural language interface to SQL type databases, synonymous paraphrasing of sentences, syntactic error correction mod黮e, and a computer-assisted language learning tool. Emphasis of this paper is laid on a new mod黮e of the processor responsible for the interface with the Universal Networking Language (UNL). As we know, the UNL by UN University is an artif齝ial language in the form of a semantic network for computers to express and exchange every kind of information.The UNL mod黮e of ETAP-3 naturally combines the two maj鰎 approaches accepted in machine translation: the transfer-based approach and the interlingua approach.更多还原