基于SKOS的学术期刊文本资源多粒度语义标注方法研究

A SKOS-based Multi-granularity Semantic Annotation Method for Academic Journal Text Resource

[目的／意义]针对学术期刊文本资源语义标注仍存在的通用本体难以构建、标注粒度单一两大问题。提出基于SKOS的学术期刊多粒度语义标注方法，从而进一步推进语义标注的应用发展，更好满足用户的多粒度学术信息需求。[方法／过程]在对《中国汉语主题词表》进行SKOS描述的基础上，以学术期刊文本资源为对象，实现其多粒度语义标注，并通过实证研究验证该方法的可行性。[结果／结论]利用SKOS实现对学术期刊文本资源进行多粒度语义标注，较之当前学术检索系统中的标注结果，在“查全”“查准”“内部特征检索入口”“检索结果反馈形式”4个方面具有一定优势。

[ Purpose/significance ] Semantic annotation for academic journals is facing two major problems which are how to embody all the concepts in oneontology and mostannotation methods are single granularity semantic annotation models. This paper proposes a SKOS-based multi-granularity semantic annotation method for academic journal text re- source, which holds great significance to the development of semantic annotation and provides a method to meetusers＇ aca- demic information demands. [ Method/process] With the SKOS description of thesaurus,this paper takes academic jour- nal text for example to achieve a multi-granularity semantic annotation method and carry on an empirical study. [ Result/ conclusion] By setting up the experimental group and the control group respectively, the paper evaluates the annotation effect of the SKOS-based multi-granularity semantic annotation method.