摘要
网络资源的语义标注和语义挖掘是当前信息检索研究的重点和难点。为挖掘网络文本的语义,根据句子的句法结构和句中谓词分析出各实词在句中所承担的语义角色,并作出相应的语义标注。文章根据对网络标注流程和功能的分析,构建了网络标注模型,旨在将基于汉语框架本体的语义标注技术应用于互联网,为未来问答式、对话式的智能化检索服务。
Semantic annotation and semantic mining of network resources is the emphasis and difficulty in the current information retrieval study. For mining the network text semantics, according to the syntactic structure of the sentence and sentence predicate analysis the semantic role of every content word in sentence, and make corresponding semantic annotation. The paper based on the analysis of network annotation processes and functions, constructing the network model. Aimed at the semantic annotation technique based on the framework of Chinese ontology will be applied to the Internet, service for future question-and-answer and dialogue type intelligent retrieval service.
作者
赵文娟
Zhao Wenjuan(Business college of ShanXi University Taiyuan 030031)
出处
《办公自动化》
2017年第19期25-28,共4页
Office Informatization
基金
山西大学商务学院院级科研课题:基于汉语框架的网络事件抽取及相关算法研究(2016009)
关键词
框架本体
语义标注
网络标注
标注模型
Framework ontology Semantic annotation Network annotation Annotation model