基于句法和语义的英汉翻译记忆系统  

English-Chinese Translation Memory System Based on Syntax and Semantics

作　　者：谢宛玲 XIE Wanling(Office of International Cooperation and Exchange,Xi’an Medical University,Xi’an 710021,China)

机构地区：[1]西安医学院,国际合作与交流办公室,陕西西安710021

出　　处：《微型电脑应用》2022年第10期179-181,共3页Microcomputer Applications

摘　　要：设计一种基于句法和语义的英汉翻译记忆系统,该系统是基于数据记忆库进行句子的翻译,可以避免大量重复工作,有助于提升专业翻译的工作效率。在进行翻译时,系统对句子的句法结构进行分析,通过相似度计算得出该句子与记忆库中资料的相似度。若存在相似度为1的句子,则直接给出译文;若与记忆库中所有句子的相似度均为0,则人工翻译,并将结果储存到记忆库;若相似度处于0~1,则依据相似度最高的句子进行翻译,然后经过人工复检得到译文,并储存于记忆库中。在不同的翻译工作中,数据记忆库不断进行扩充,翻译记忆系统的功能逐渐强大。An English-Chinese translation memory system based on syntax and semantics is designed.The system is operated based on data memory database for sentence translation.A lot of repetitive work can be avoided and the efficiency of professional translation can be improved.In the process of translation,the syntactic structure of the sentence is analyzed,and the similarity between the sentence and the data in the memory database is calculated.If similarity is 1,the translation is given directly;if the similarity with all the sentences in the memory database is 0,the translation is conducted manually and the results are stored in the memory database;if the similarity is between 0 and 1,the translation is carried out according to the sentence with the highest similarity,and the results are checked manually and stored in the memory database.In different translation projects,data memory database can be constantly expanded,and the function of translation memory system will become more and more powerful.

关 键 词：句法结构分析 相似度计算 记忆库设计 翻译记忆技术 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]