Abstrac tA prototype information retrieval system wa s developed that gives users fast and easy access to textua l information . This system uses a statistical ranking methodology that allows a user to input a query usin g only natural language, such as a sentence or a nou n phrase, with no special syntax required. The syste m returns a set of text titles or descriptions, ranked in order of likely relevance to the query . The user can then select one or more titles for further examination of th e corresponding text . The prototype was tested by ove r forty users, all proficient in doing manual research in th e subject area, but few proficient in doing online research . The system was very fast, providing response times on the order of one second for searching a gigabyte of dat a and was also very effective, retrieving at least on e relevant record within the first ten records retrieved fo r 53 out of 68 test queries. All users were able to ge t satisfactory results within a short time after seeing a demonstration, and those that had never used an onlin e retrieval system did as well as those with experience . This is in sharp contrast to Boolean based retrieva l systems where continual use is necessary to obtai n consistently good results .
SIGCHI Bulletin July 1990