DocumentCode :
3230392
Title :
A relevance feedback retrieval system based on indri toolkit
Author :
Liu, Chun-Bo ; Li, Yan ; Xu, Wei-ran ; Li, Si ; Guo, Jun
Author_Institution :
Sch. of Inf. & Commun., Beijing Univ. of Posts & Telecommun., Beijing, China
fYear :
2011
fDate :
27-29 May 2011
Firstpage :
4
Lastpage :
7
Abstract :
Relevance feedback is an important application in information retrieval on Internet. This paper introduces a relevance feedback retrieval system to improve the searching results. The system is built on the Indri toolkit, using pseudo relevance feedback method. First, we introduce the framework of the relevance feedback system and the methods we used in each module. The main module of the system is relevance feedback module. In this module, our algorithm called KNN-KL-LM algorithm is introduced in details for query expansion, which is essential for relevance feedback. Experiments show that the retrieval results are obviously improved.
Keywords :
Internet; learning (artificial intelligence); pattern classification; query processing; relevance feedback; Internet; KNN-KL-LM algorithm; indri toolkit; information retrieval; pseudo relevance feedback method; query expansion; relevance feedback retrieval system; Indri; KL-divengence; KNN; Language Model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-61284-485-5
Type :
conf
DOI :
10.1109/ICCSN.2011.6014205
Filename :
6014205
Link To Document :
بازگشت