Bringing natural language information retrieval out of the closet

Publisher Website
Google Scholar
Abstract
A prototype information retrieval system was developed that gives users fast and easy access to textual information. This system uses a statistical ranking methodology that allows a user to input a query using only natural language, such as a sentence or a noun phrase, with no special syntax required. The system 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 the corresponding text. The prototype was tested by over forty users, all proficient in doing manual research in the 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 data and was also very effective, retrieving at least one relevant record within the first ten records retrieved for 53 out of 68 test queries. All users were able to get satisfactory results within a short time after seeing a demonstration, and those that had never used an online retrieval system did as well as those with experience. This is in sharp contrast to Boolean based retrieval systems where continual use is necessary to obtain consistently good results.

This publication has 6 references indexed in Scilit: