汉字和汉语的计算机处理  

The computer processing of Chinese characters and Chinese language

作　　者：冯志伟[1] 

机构地区：[1]国家语言文字工作委员会

出　　处：《当代语言学》2001年第1期1-21,共21页Contemporary Linguistics

摘　　要：本文从汉字输入与汉语语料库、语料库中汉语书画文本的自动切词、语料库中汉语书面文本的词性(POS)自动标注、语料库中汉语书面文本的自动短语定界与句法标注、机器词典的建造、术语数据库的建造、机器翻译、计算机辅助文本校对、情报自动检索、汉语语音自动识别、汉语语音自动合成、汉字自动识别等12个方面,介绍我国汉字和汉语的计算机处理的研究情况。The author describes the computer processing of Chinese characters and Chinese language. The following aspects are discussed in detail:the various input approaches of Chinese characters and Chinese corpus, the automatic segmentation, the automatic POS tagging, the automatic phrase bracketing and syntactic annotation of Chinese written text, electronic dictionary, terminological databank, machine translation, computer-aided proofreading, automatic information retrieval,automaticChinese speechrecognition and synthesis,and automatic Chinese characters recognition.

关 键 词：汉字输入 汉语语料库 机器翻译 计算机技术 自动标注 

分 类 号：H08[语言文字—语言学]