大规模语料中NV搭配对的提取方法研究  

A Research on the Acquiring Method of the NV Collocation from the Large Corpus

作　　者：辛日华[1] 

机构地区：[1]呼伦贝尔学院计算机科学与技术学院,内蒙古呼伦贝尔021008

出　　处：《内蒙古大学学报（自然科学版）》2013年第6期624-630,共7页Journal of Inner Mongolia University：Natural Science Edition

基　　金：内蒙古自然科学基金资助(No.2013MS0102)

摘　　要：词汇语义知识是自然语言处理(NLP)必须依靠的基础资源,NLP所涉及到的诸多问题中,多义词的识别与消歧是一个焦点环节.而词语之间的搭配知识是支持词义排歧的基础资源.词语搭配作为描述词间组合能力的一种重要的词汇知识,在自然语言处理中具有重要作用,也是语义学研究中的基础性课题.动词在汉语信息处理中是句子的核心,是计算机对汉语进行分析和处理的基础.研究在大规模语料库中进行名词(Noun)和动词(Verb)搭配对的提取方法,即建立一个包含名词词义、名词、名词对应的动词及动词相应的词义等内容的数据库,以供词义排歧使用.Lexical knowledge is the basic resource of Natural Language Precessing （NLP）and word sense disambiguation is one focus of many problems concerning NLP. The knowledge of word collocation is the basic resource for NLP acquiring. Collocation which serves as an important vocab- ulary knowledge in describing the word--building ability, plays an important role in natural lan- guage processing,and is an elementary subject in the field of semantics. Verb is the centre of Chi- nese information processing and is the basis of computer in analysing and processing Chinese. The extracting method of NV collocation pairs for the noun and verb is studied in the large corpus,that is to say,a database is built including senses of nouns,nouns,verbs corresponding nouns and senses of verbs to support word sense disambiguation.

关 键 词：词义知识 语料库 NV搭配对 词义排歧 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]