Issue No. 02 - March/April (2003 vol. 18)
Y. He , University of Cambridge
S.C. Hui , Nanyang Technological University
A.C.M. Fong , Massey University
<p>Many scholarly publications are currently available on the Internet and in digital libraries. However, existing search engines have proved mostly ineffective in searching these publications. Using scholarly literature published on the Internet as a case study, the authors developed a publication retrieval system that consists of a citation indexing agent and an intelligent retrieval agent. The citation indexing agent searches the Internet for relevant scholarly publications and generates a citation database accordingly. The intelligent retrieval agent then helps retrieve the scholarly publications. The retrieval technique is based on Kohonen?s self-organizing map. The proposed technique comprises a training process of mining the citation database to generate cluster information and a retrieval process for retrieving and ranking the publications according to user input queries. This technique offers fast retrieval speeds and high retrieval precision in terms of document relevance.</p>
citation indexing, information retrieval, KSOM neural network, scholarly publications
A. Fong, S. Hui and Y. He, "Citation-Based Retrieval for Scholarly Publications," in IEEE Intelligent Systems, vol. 18, no. , pp. 58-65, 2003.