Show simple item record

dc.contributor.author苏新春
dc.contributor.author杜晶晶
dc.date.accessioned2016-07-01T08:17:36Z
dc.date.available2016-07-01T08:17:36Z
dc.date.issued2014-2-15
dc.identifier.citation语言文字应用,2014,(1):12-21
dc.identifier.issn1003-5397
dc.identifier.otherYYYY201401003
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/126593
dc.description.abstract词语库与规则库是在“多义词词义搭配知识库“中起基础与核心作用的两个子库。词语库有两个来源,一是词典词,二是真实语料词,两类词语有着书面语与口语词、正体词与异体词、语言词与言语词、通用词与领域词、稳定词与具体词等方面的差异。词语库特点会在很大程度上影响到词义标注的效果与正确率。纳入首批考察的词语为双音节多义词3771条,共有义项7861个。规则库统摄语义库、义项库、语料库,这些知识库通过规则库的组织而发挥作用。规则库是实现词义标注工程目标的直接依据,对于任何一个多义词,规则定义的多寡有无、质量好坏都会直接影响标注结果。规则库集中体现SCT整个系统的意义与价值,是语言知识与工程实施的结晶体。
dc.description.abstractWord base and rule base are the two central and fundamental subsets of The Polysemy Sense Collocation Knowledge Base.Word base is comprised of words from dictionaries and words from corpora.They differentiate in written words and spoken words, standard words and variants,language words and speech words,general words and domain words,stable words and concrete words,etc.The characteristics of word base will to a large extent affect the result and accuracy of word sense tagging.The first study includes 3771 polysemou disyllables with 7861 word senses.The semantic base,sense base and corpus are subject to the organization of rule base.Rule base is a direct basis for word sense tagging.For any of the polysemous words,tagging depends on the quality and quantity of rule definition.It also epitomizes the significance and value of the whole SCT system,and is the combination of linguistic knowledge and word sense tagging.
dc.language.isozh_CN
dc.subject多义词
dc.subject词义搭配知识库
dc.subject词语库
dc.subject规则库
dc.subjectpolysemous words
dc.subjectword sense collocation knowledge base
dc.subjectword base
dc.subjectrule base
dc.title词语库的收词与规则库的建立
dc.title.alternativeThe Word-Collection of Word Base and The Establishment of Rule Base
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record