Using a Natural Language Understanding System to Generate Semantic Web Content

Akshay Java, Sergei Nirenburg, Marjorie McShane, Tim Finin, Jesse English, and Anupam Joshi

October 16, 2006

We describe our research on automatically generating rich semantic annotations of text and making them available on the Semantic Web. In particular, we discuss the challenges involved in adapting the OntoSem natural language processing system for this purpose. OntoSem, an implementation of the theory of ontological semantics under continuous development for over 15 years, uses a specially constructed NLP-oriented ontology and an ontological-semantic lexicon to translate English text into a custom ontology-motivated knowledge representation language, the language of text meaning representations (TMRs). OntoSem focuses on a variety of ambiguity-resolution tasks, as well as processing unexpected input and reference. To adapt OntoSem results to the Semantic Web, we developed a translation system, OntoSem2OWL, between the TMR language and the Semantic Web language OWL. We then used OntoSem and OntoSem2OWL to support SemNews. This experimental web service monitors RSS news sources, processes news-story summaries, and publishes a structured representation of the text's meaning.

BibTeX OWL Tweet Scholar

Tags: agent, ai, natural language processing, ongology, ontosem, owl, rdf, semantic web, semnews

Type: TechReport

Publisher: UMBC

Note:

Downloads: 3453 downloads