Annotating the World Wide Web using Natural Language

This paper describes the START Information Server built at the MIT Arti cial Intelligence Laboratory Available on the World Wide Web since December the START Server provides users with access to multi media information in response to questions for mulated in English Over the last years the START Server answered hundreds of thousands of questions from users all over the world The START Server is built on two foundations the sentence level Natural Language processing capabil ity provided by the START Natural Language system Katz and the idea of natural language annota tions for multi media information segments This pa per starts with an overview of sentence level process ing in the START system and then explains how an notating information segments with collections of En glish sentences makes it possible to use the power of sentence level natural language processing in the ser vice of multi media information access The paper ends with a proposal to annotate the WorldWide Web