基于网络爬虫和文本挖掘的实体关系研究与实现

Research on Entity Relationship Based on Web Crawler and Text Mining

随着网络资源的不断膨胀,有关生物文献资源越来越多,生物学家急需各种自动化的技术从海量文献中抽取有价值的信息。基于网络爬虫和文本挖掘的技术,设计研发一个用于挖掘网络上电子版论文中实体关系的系统,并且使用该系统,成功挖掘有关疾病和基因的关系。

With the continuous increase of web resource, more and more document resource emerges, biologists are urgent to get valuable informa- tion from huge document by using a variety of automatics technique. Based on the development of web crawler and text mining, designs a novel system to excavate the entity relationship among electronic papers on the internet and apply successfully such system to catch the relation between disease and gene.