Neural Relevance Feedback for Information Retrieval

Relevance feedback is a technique used in interactive Information Retrieval (IR) systems to enable a user to provide additional information to help the system identify more relevant documents. The additional information is provided in the form of relevance judgements on retrieved documents. One of the most advanced relevance feedback technique in operative IR system is based on a probabilistic function. Recent results show that it is possible to implement relevance feedback also using neural networks. This paper presents the results of an experimental investigation into the use of the Back Propagation learning algorithm for implementing relevance feedback. The investigation compares the performance of the proposed neural relevance feedback technique against to and in combination with probabilistic relevance feedback. The results obtained seem to indicate that, while probabilistic relevance feedback often outperforms neural relevance feedback, the combination of the two techniques is more effective than both techniques taken separately.

[1]  Fabio Crestani,et al.  Implementation and Evaluation of a Relevance Feedback Device Based on Neural Networks , 1995, IWANN.

[2]  L. B. Lmeida.  Backpropagation in perceptrons with feedback , 1988 .

[3]  Ricardo Baeza-Yates,et al.  Information Retrieval: Data Structures and Algorithms , 1992 .

[4]  Michael Keen,et al.  ASLIB CRANFIELD RESEARCH PROJECT FACTORS DETERMINING THE PERFORMANCE OF INDEXING SYSTEMS VOLUME 2 , 1966 .

[5]  Donna K. Harman,et al.  Relevance Feedback and Other Query Modification Techniques , 1992, Information retrieval (Boston).

[6]  Andrew Jennings,et al.  A Personal News Service Based on a User Model Neural Network , 1992 .

[7]  Donna K. Harman,et al.  Ranking Algorithms , 1992, Information Retrieval: Data Structures & Algorithms.

[8]  Fabio Crestani,et al.  Soft Information Retrieval : Applications of Fuzzy Set Theory and Neural Networks , 1999 .

[9]  F. Crestani.  Comparing neural and probabilistic relevance feedback in an interactive information retrieval system , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[10]  Stephen E. Robertson,et al.  Relevance weighting of search terms , 1976, J. Am. Soc. Inf. Sci..

[11]  K. Sparck Jones,et al.  INFORMATION RETRIEVAL TEST COLLECTIONS , 1976 .

[12]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[13]  Fabio Crestani.  Domain Knowledge Acquisition for Information Retrieval using Neural Networks , 1996 .

[14]  Gerard Salton,et al.  Automatic Information Organization And Retrieval , 1968 .

[15]  C. J. van Rijsbergen,et al.  An Evaluation of feedback in Document Retrieval using Co‐Occurrence Data , 1978, J. Documentation.

[16]  W. Bruce Croft.  Approaches to Intelligent Information Retrieval , 1987, Inf. Process. Manag..

[17]  Fabio Crestani,et al.  “Is this document relevant?…probably”: a survey of probabilistic models in information retrieval , 1998, CSUR.

[18]  Mark Sanderson,et al.  NRT: News Retrieval Tool , 1991, Electron. Publ..

[19]  L. R. Rasmussen,et al.  In information retrieval: data structures and algorithms , 1992 .

[20]  J. Huisman.  The Netherlands , 1996, The Lancet.

[21]  Mark D. Dunlop.  The effect of accessing nonmatching documents on relevance feedback , 1997, TOIS.