Embedded grammar tags: advancing natural language interaction on the Web

Author

Dorai, Gautham K. ; Yacoob, Yaser

Author_Institution

Inst. for Adv. Comput. Studies, Maryland Univ., College Park, MD, USA

Volume

17

Issue

1

fYear

2002

Firstpage

48

Lastpage

53

Abstract

Embedded grammar tags (EGTs) reflect Web page content by anticipating queries users might launch to retrieve that content. The grammars provide a unifying component for speech recognition engines, semantic Web page representation, and speech output generation. We propose a new framework that lets intelligent agents discover accurate, 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.

Keywords

Internet; grammars; information resources; natural languages; search engines; software agents; speech recognition; Web page content; embedded grammar tags; information content; intelligent agents; natural language interaction; natural language queries; semantic Web page representation; speech output generation; speech recognition engines; HTML; Intelligent agent; Internet; Markup languages; Natural languages; Resource description framework; Search engines; Semantic Web; Technical Activities Guide -TAG; XML;

fLanguage

English

Journal_Title

Intelligent Systems, IEEE

Publisher

ieee

ISSN

1541-1672

Type

jour

DOI

10.1109/5254.988450

Filename

988450