个人信息Personal Information
教授
博士生导师
硕士生导师
性别:男
毕业院校:大连理工大学
学位:博士
所在单位:计算机科学与技术学院
电子邮箱:yangzh@dlut.edu.cn
Two phase indexes based passage retrieval in biomedical texts
点击次数:
论文类型:会议论文
发表时间:2007-09-14
收录刊物:EI、CPCI-S
卷号:4688
页面范围:746-755
关键字:passage retrieval; sentence-level half-overlapped windows; retrieval models
摘要:The biomedical literature is growing at a double-exponential pace. Passage-level retrieval is more effective to provide the information section than document-level retrieval. This paper presents a method of two phase indexes based passage retrieval. First two phase indexes: paragraph index and sentence-level half-overlapped windows index are built. Then, BM25 model is used to retrieval on the two phase indexes. At last, the passage and paragraph retrieval results are combined as the result of the passage retrieval. The experiment result shows that the performance is improved 5% with two phase indexes than only with the paragraph index.