Entry Date:
January 10, 1999

InfoLab Group (START: Natural Language Question Answering System)

Principal Investigator Boris Katz

Co-investigators Susan L Felshin , Gary C Borchardt

Project Website http://start.csail.mit.edu/


The MIT InfoLab Group develops intelligent interactive software systems that help people access information and solve problems on human terms. The lab conducts research in natural language processing and multimedia information access.

A key component of this effort is the START Natural Language System. START provides access to text, diagrams, images, video and audio clips, data sets, Web pages and other types of information in response to questions posed to it in English. START works by using a technique called "natural language annotation," in which retrievable information segments are associated with natural language sentences and phrases -- annotations -- that describe their contents. Information segments are then retrieved when their annotations semantically match particular user-submitted questions.

Two applications of START are currently available for use through the World Wide Web. The Globe Server provides access to information about cities and countries of the world, including maps, weather reports, and factual information. The AI Lab Server provides access to information about the MIT Artificial Intelligence Laboratory, its members, and the research they do. In addition, we are developing a News Server, which will provide access to news stories and other timely information available from selected Web-based resources.

Another component of the group's effort involves the development of IMPACT, an interactive planning and monitoring system grounded in simple, stylized English accounts of circumstances and events.