摘要
[目的 /意义]针对共词分析存在的普遍问题,提出一种基于细粒度语义分析的共词网络构建与分析方法。[方法 /过程]借助SemRep实现源文本主题概念及其语义关系的规范化抽取并由此构建语义共词网络,然后以节点的中心度和边的频次为指标对内容特征词进行抽取,利用UMLS语义网络规定的语义搭配模式,通过概念-语义类型-语义类型组的两级映射,对语义述谓项进行类团划分。[结果 /结论]通过与常规共词分析方法比较,发现基于细粒度语义关系的共词分析能有效地揭示文本主题内容,利用UMLS语义网络资源能从语义学角度清晰准确地对语义共词网络进行类团划分。
[ Purpose/significance ] To solve the general problems in co-word analysis, we propose a method for constructing and analyzing fine-grained semantic co-word network. [ Method/process ] The standard concepts and semantic relations between concepts were extracted from the source text with SemRep and hence the semantic co-word network was built. The feature words were extracted according to the centrality of the nodes and the frequency of the edges. The seman- tic predications were grouped based on the semantic schema defined by UMLS semantic network and the mapping from con- cept to its semantic type and semantic type to semantic type group. [ Result/conclusion] Compared with routine co-word analysis method, the fine-grained semantic co-word analysis we proposed can effectively represent the content for source text. UMLS semantic network can be used to partition the semantic co-word network accurately.
出处
《图书情报工作》
CSSCI
北大核心
2016年第11期135-142,共8页
Library and Information Service
基金
教育部人文社会科学研究青年基金项目"基于语义述谓网络属性的多文档自动摘要:以生物医学为例"(项目编号:13YJC870030)研究成果之一
关键词
语义共词网
共词分析
细粒度
网络分析
semantic co-word network co-word analysis fine granularity network analysis
