An overview is presented of recently completed research investigating three questions: what does it mean for a computer to know what it knows about? How can a computer construct a representation of what it knows about? How can such a representation be used for practical applications that advance the state-of-the-art in understanding the content of large databases?.>

Indexing text for accurate retrieval ZS a dificuli and in)portant problem.. On-ltne information services generally depend on "keyword" mdtces rather ihat~other methods of retrieval, because of the pract~cal jealures of keywords for storage, dtssemtnatlonj and browsing m well as for

Neither natural language processing nor information retrieval is any longer a young field, but the two areas have yet to achieve a graceful interaction. Mainly, the reason for this incompatibility is that information retrieval technology depends upon relatively simple but robust methods, while natural language processing involves complex knowledge-based systems that have never approached robustness. We provide an analysis of areas in which natural language and information retrieval come together, and describe a system that joins the two fields by combining technology, choice of application area, and knowledge acquisition techniques.

Neither natural language processing nor information retrieval is any longer a young field, but the two areas have yet to achieve a graceful interaction. Mainly, the reason for this incompatibility is that information retrieval technology depends upon relatively simple but robust methods, while natural language processing involves complex knowledge-based systems that have never approached robustness. We provide an analysis of areas in which natural language and information retrieval come together, and describe a system that joins the two fields by combining technology, choice of application area, and knowledge acquisition techniques.