摘要
设计并实现了中文领域术语抽取系统,提出了基于前后缀的中文领域术语抽取算法,该算法独立于具体的领域,并且对包含常用前后缀的领域术语具有较好的抽取效果;通过对领域本体构建中关键技术的研究,提出了适用于不同领域的领域本体半自动构建方法;最后,数字图书馆气候变化领域本体的成功构建验证了基于多源数据的领域本体半自动构建方法的有效性,并且该方法可以很方便地移植到其他领域。
A Chinese field terminology extraction system was designed and implemented. The Chinese field terminology extraction algorithm based on prefix and suffix is proposed,which is independent of the specific fields,and has good extraction effect for the field terminology with commonly-used prefixes and suffixes. The key technology of field ontology construction is studied,and the field ontology semiautomatic construction method suitable for different fields is proposed. The climate change field ontology for digital library was constructed successfully,which verified that the field ontology semiautomatic construction method based on multi-source data is effective,and the method can be easily transplanted to other fields.
出处
《现代电子技术》
北大核心
2016年第17期112-115,共4页
Modern Electronics Technique
基金
河南省教育厅科学技术研究重点项目:高职高专图书馆信息化建设中的成本控制研究(13B790259)
关键词
本体
本体构建
术语抽取
关系抽取
ontology
ontology construction
terminology extraction
relation extraction
