An Information Retrieval System for Improving Efficiency in Scientific Literature Searches: Progress Report #1

This reports details the work completed in the first three months of development of the QCS (Query, Cluster, Summarize) information retrieval (IR) system. In the first section, the project as it was originally proposed is briefly presented. (For a more detailed account of the proposal, an interested reader is directed to the original proposal [Dun].) Sections 3, 4, and 5 give the details of the algorithms implemented in the current QCS system. Implementation issues are discussed in Section 6, highlighting work completed to date on the QCS system, a user interface to the system, and accompanying software tools created or utilized in facilitating the development of the QCS system. As with many software projects of this scale, some of the ideas originally proposed for the QCS system in [Dun] have been phased out for various reasons. The specific changes and the rationale behind these changes are discussed in Section 7. Finally, a plan for the completion of Version 1.0 of the QCS IR system is presented in Section 8.