JSAI2018

Presentation information

Oral presentation

General Session » [General Session] 9. NLP / IR

[1J2] [General Session] 9. NLP / IR

Tue. Jun 5, 2018 3:20 PM - 5:00 PM Room J (2F Royal Garden B)

座長:木村 泰知(小樽商科大学)

3:40 PM - 4:00 PM

[1J2-02] Experimental Analysis of Effect of Reducing Search Space for Relevance Feedback Based on SVM

〇Yuto Imamura1, Takahiro Nishigaki1, Takashi Onoda1 (1. Aoyama Gakuin University)

Keywords:Support Vector Machines, relevance feedback, search space

SVM (Support Vector Machines) based relevance feedback has proposed. Vector space model is often used for document retrieval. At that time, the search space may become very large because the document vectors have too many attributes which included in the documents on the database. It is presumed that search performance decreases due to the presence of meaningless attributes. However, it is not clear the effect of the size of the search space for the search performance. Therefore, we compare among eight search spaces and conducted an experiment. The search space based on attributes included in the presentation documents improved search performance.