A multimodal restaurant finder for semantic web

Multimodal dialogue systems provide multiple modalities in the form of speech, mouse clicking, drawing or touch that can enhance human-computer interaction. However, one of the drawbacks of the existing multimodal systems is that they are highly domain-specific and they do not allow information to be shared across different providers. In this paper, we propose a semantic multimodal system, called Semantic Restaurant Finder, for the Semantic Web in which the restaurant information in different city/country/language are constructed as ontologies to allow the information to be sharable. From the Semantic Restaurant Finder, users can make use of the semantic restaurant knowledge distributed from different locations on the Internet to find the desired restaurants.