AeroDAML: Applying Information Extraction to Generate DAML Annotations from Web Pages.
Paul A. Kogut, William S. Holmes · 2001
The DARPA Agent Markup Language (DAML) is an emerging knowledge representation for the Semantic Web. DAML can encode the semantics of a document for use by agents on the web. However, DAML annotation of documents and web pages is a tedious and time consuming task. AeroDAML is a knowledge markup tool that applies natural language information extraction techniques to automatically generate DAML annotations from web pages. AeroDAML links most proper nouns and common relationships with classes and properties in DAML ontologies. This paper discusses the design of AeroDAML including linguistic and practical issues related to semantic annotation. Keywords Natural language processing, semantic markup, information extraction, software agents