The Community for Technology Leaders
Green Image
<p>The explosive expansion in Web content has not been accompanied by correspondingly powerful search and content analysis engines. Recent efforts to expand markup languages aim to enhance the effectiveness of content recovery from Web pages by embedding tags that might guide a search engine in uncovering the meaning of information. The authors propose a new framework that lets intelligent agents discover accurate and concise responses to natural language queries. This framework's backbone consists of embedded grammar tags that capture natural language queries. EGTs reflect information content in Web pages by anticipating the queries that users might launch to retrieve particular content. The grammars provide a unifying component for speech recognition engines, Semantic Web page representation, and speech output generation. The authors demonstrate how EGTs can enable a software agent to respond to natural speech input from users in narrow domains such as weather, the stock market, and faculty homepages.</p>
Internet content, markup languages, natural language speech, Semantic Web, user interface, XML

G. K. Dorai and Y. Yacoob, "Embedded Grammar Tags: Advancing Natural Language Interaction on the Web," in IEEE Intelligent Systems, vol. 17, no. , pp. 48-53, 2002.
92 ms
(Ver 3.3 (11022016))