High-speed data search

Abstract

The high-speed data search system developed for KSC incorporates existing and emerging information retrieval technology to help a user intelligently and rapidly locate information found in large textual databases. This technology includes: natural language input; statistical ranking of retrieved information; an artificial intelligence concept called semantics, where 'surface level' knowledge found in text is used to improve the ranking of retrieved information; and relevance feedback, where user judgements about viewed information are used to automatically modify the search for further information. Semantics and relevance feedback are features of the system which are not available commercially. The system further demonstrates focus on paragraphs of information to decide relevance; and it can be used (without modification) to intelligently search all kinds of document collections, such as collections of legal documents medical documents, news stories, patents, and so forth. The purpose of this paper is to demonstrate the usefulness of statistical ranking, our semantic improvement, and relevance feedback.