SP500207 Query Improvement in INformation Retrieval Using Genetic Algorithms - A Report on the Experiments of the TREC Project chapter J. Yang R. Korfhage E. Rasmussen National Institute of Standards and Technology Donna K. Harman Query Improvement In Information Retrieval Using Genetic Algorithms - A Report on the Experiments of the TREC Project Jing-Jye Yang, Robert R. Korfhage Department of Information Science and Edie Rasmussen Depar[OCRerr]ment of Library Science School of Library and Information Science University of Pittsburgh Abstract We have been developing an adaptive method using genetic algorithms to modi[OCRerr] user queries, based on relevance judgments. This algorithm was adapted for the Text REtrieval Conference (TREC). The method is shown to be applicable to large text collections, where more relevant documents are presented to users in the genetic modification. The algorithm also shows some interesting phenomena, such as parallel searching. Further studies are planned to adjust the system parameters to improve its effectiveness. 1. Introduction Information retrieval can be viewed as searching in a high-dimensional document space to bring relevant documents to users. It is known, however, that this is not an easy task. Due to the complexity of document writing styles and the difficulty users have in presenting their information requests, the retrieval results often frustrate users. Returning to the system with a modified query becomes unavoidable if a user wants to improve the retrieval results. However, most systems provide litde or no guidance to the user for modif[OCRerr]ing the original query, adding to the frustration. Using relevance feedback to help users solve the problem has long being viewed as a promising agenda. 31