The use of genetic programming to build queries for information retrieval

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Kraft:1994:GPqir,

• author = "Donald H. Kraft and Frederick E. Petry and Bill P. Buckles and Thyagarajan Sadasivan",
• title = "The use of genetic programming to build queries for information retrieval",
• booktitle = "Proceedings of the 1994 IEEE World Congress on Computational Intelligence",
• year = "1994",
• volume = "1",
• pages = "468--473",
• address = "Orlando, Florida, USA",
• month = "27-29 " # jun,
• publisher = "IEEE Press",
• keywords = "genetic algorithms, genetic programming, Boolean query formulation, fitness function, index term space, information retrieval system, parse tree, relevance feedback, topicality, user defined measures, Boolean functions, information retrieval systems, query processing, search problems, trees (mathematics), vocabulary",
• DOI = "doi:10.1109/ICEC.1994.349905",
• size = "6 pages",
• abstract = "Genetic programming is applied to an information retrieval system in order to improve Boolean query formulation via relevance feedback. This approach brings together the concepts of information retrieval and genetic programming. Documents are viewed as vectors in index term space. A Boolean query, viewed as a parse tree, is an organism in the genetic programming sense. Through the mechanisms of genetic programming, the query is modified in order to improve precision and recall. Relevance feedback is incorporated, in part, via user defined measures over a trial set of documents. The fitness of a candidate query can be expressed directly as a function of the relevance of the retrieved set. Preliminary results based on a testbed are given. The form of the fitness function has a significant effect upon performance and the proper fitness functions take into account relevance based on topicality (and perhaps other factors)",
• notes = "Syntax of programs restricted to Boolean disjunctive normal form. Has 4923 terms (=terminals?), seeds initial population so 80% of terms are predetermined to be relevant, rest chosen at random. 20% mutation rate (three kinds). Fitness ~ relevance of documents retrieved.",

}

Genetic Programming entries for Donald H Kraft Frederic E Petry Bill Buckles Thyagarajan Sadasivan

Citations