A comparison of classifiers and document representations for the routing problem
SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
Journal of the American Society for Information Science
Exploring the similarity space
ACM SIGIR Forum
Applying genetic algorithms to query optimization in document retrieval
Information Processing and Management: an International Journal
Computational Intelligence techniques for Web personalization
Web Intelligence and Agent Systems
An online blog reading system by topic clustering and personalized ranking
ACM Transactions on Internet Technology (TOIT)
Evolving new lexical association measures using genetic programming
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
Journal of Computational Methods in Sciences and Engineering - Intelligent Systems and Knowledge Management (Part II)
An adaptive learning automata-based ranking function discovery algorithm
Journal of Intelligent Information Systems
Hi-index | 0.00 |
Search engines contain programs that compare the words in a user's query to the words and phrases in Web pages. This comparisonemphasizes relatively rare terms, terms that occur frequently in a page, and terms in prominent positions (such as a page's title), amongother textual clues that suggest what the page is about. Although all search engines differ in the ways they determine which Web pages topresent to a user, each incorporates a method that its designers hope will be effective. Nonetheless, retrieval algorithms performinconsistentlysome better in one circumstance, others in another--with no way to know in advance which will be most effective. Theauthors approach retrieval from a learning perspective. Rather than determining how to combine lexical clues beforehand, they infer howthis should be done on the basis of users' evaluations of previously viewed documents. Unlike conventional systems, this approachautomatically evolves new retrieval programs through genetic programming. It seems particularly effective for users whose need forinformation remains consistent over weeks or months.