摘要
文本过滤是指从大量的文本中寻找满足用户需求的文本的过程。以互联网上下载的突发事件新闻文本为研究背景,提出了基于新闻标题的文本过滤模型,根据示例文本构建标题过滤模板,采用基于关键字的过滤方法对突发事件新闻文本进行过滤。其特点是实现简单,过滤速度快,有一定的实际作用。
Text filtering is the procedure of retrieving documents relevant to the requirements of specific users from a largescale text data stream. The paper takes the news about the accident reported on Web as background, and puts forward text filtering model on news title. It creats filtering profile on title by example texts, and filters accident news text by the method based on keys. This model can accomplish text filtering simply and quickly, and perform well too.
出处
《电脑开发与应用》
2010年第4期1-2,14,共3页
Computer Development & Applications
基金
国家自然科学基金资助项目(60475022)
关键词
文本过滤
标题过滤模板
文本过滤模型
text filtering, filtering profile on title, text filtering model
