“现代汉语语义词典”的结构及应用  

Structure and Application of The Semantic Knowledge-base of Modern Chinese

作　　者：王惠[1] 詹卫东[2] 俞士汶[2] 

机构地区：[1]新加坡国立大学中文系,新加坡117570 [2]北京大学,北京100871

出　　处：《语言文字应用》2006年第1期134-141,共8页Applied Linguistics

基　　金：国家973重点基础研究项目(G1998030507-4)和(G1998030507-1)资助

摘　　要：“现代汉语语义词典(SKCC)”是一个面向汉英机器翻译的大规模汉语语义知识库,它以数据库文件形式收录6.6万余实词,不仅给出每个词语所属的词类、语义类,而且以义项为单位详细描述了它们的各种语义搭配限制。目的是为计算机语义自动分析、词义消歧等任务提供强有力的支持。本文介绍这部语义词典的结构、内容,并以实例说明这部词典可有效地解决翻译系统中的词汇歧义(WSD)问题。The Semantic Knowledge-base of Modern Chinese （SKMC） is a large scale bilingual semantic resource. It provides a large amount of semantic information such as semantic hierarchy and collocation features for 66539 Chinese words and their English counterparts. Its POS and semantic classification represent the latest progress in Chinese language engineering. The descriptions of semantic attributes are fairly thorough and comprehensive. The main work in this paper is to introduce the outline of SKMC, and establish a multi-level Word Sense Disambiguation （WSD） model based on it. The results indicate that the SKMC is effective for word sense disambiguatian in Chinese and are likely to be important for general Chinese Natural Language Processing （NLP）.

关 键 词：语义词典 词义消歧 词汇语义学 自然语言处理 中文 

分 类 号：H164[语言文字—汉语]