The effects of fitness functions on genetic programming-based ranking discovery for Web search: Research Articles

摘要: Genetic-based evolutionary learning algorithms, such as genetic algorithms (GAs) and programming (GP), have been applied to information retrieval (IR) since the 1980s. Recently, GP has a new IR task—discovery of ranking functions for Web search—and achieved very promising results. However, in our prior research, only one fitness function used GP-based learning. It is unclear how other may affect discovery search, especially it well known that choosing proper important effectiveness efficiency algorithms. In this article, we report experience contrasting different designs on using large corpus. Our results indicate design instrumental performance improvement. We also give recommendations genetic-based experiments. © 2005 Wiley Periodicals, Inc.