Natural language in multimodal human-computer interface

Two prototype information-access applications show how the integration of natural language and hypermedia produces systems that allow users and systems to exchange more information. The author considers how the Natural Language Group designed the ALFresco prototype to provide information on 14th-century Italian frescoes and monuments and to suggest other masterpieces that might interest the user. He also discusses the MAIA project which integrates components developed by IRST researchers in speech recognition, natural language, knowledge representation, vision, reasoning, and other areas of AI.<>