How START works!

The START Natural Language System is a software system designed to answer questions that are posed to it in natural language. START parses incoming questions, matches the queries created from the parse trees against its knowledge base and presents the appropriate information segments to the user. In this way, START provides untrained users with speedy access to knowledge that in many cases would take an expert some time to find.

START (SynTactic Analysis using Reversible Transformations) was developed by Boris Katz at MIT's Artificial Intelligence Laboratory. Currently, the system is undergoing further development by the InfoLab Group, led by Boris Katz. START was first connected to the World Wide Web in December, 1993, and in its several forms has to date answered millions of questions from users around the world.

A key technique called "natural language annotation" helps START connect information seekers to information sources. This technique employs natural language sentences and phrases -- annotations -- as descriptions of content that are associated with information segments at various granularities. An information segment is retrieved when its annotation matches an input question. This method allows START to handle all variety of media, including text, diagrams, images, video and audio clips, data sets, Web pages, and others.

The natural language processing component of START consists of two modules that share the same grammar. The understanding module analyzes English text and produces a knowledge base that encodes information found in the text. Given an appropriate segment of the knowledge base, the generating module produces English sentences. Used in conjunction with the technique of natural language annotation, these modules put the power of sentence-level natural language processing to use in the service of multi-media information access.

For more information on the START system see B. Katz, "From Sentence Processing to Information Access on the World Wide Web," AAAI Spring Symposium on Natural Language Processing for the World Wide Web, Stanford University, Stanford CA (1997).