International Journal on Semantic Web and Information Systems

Using a Natural Language Understanding System to Generate Semantic Web Content

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

November 1, 2007

We describe our research on automatically generating rich semantic annotations of text and making it 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 fifteen years, uses a specially constructed NLP-oriented ontology and an ontologicalsemantic lexicon to translate English text into a custom ontology-motivated knowledge representation language, the language of text meaning representations (TMRs). OntoSem concentrates on a variety of ambiguity resolution tasks as well as processing unexpected input and reference. To adapt OntoSem's representation to the Semantic Web, we developed a translation system, OntoSem2OWL, between the TMR language into the Semantic Web language OWL. We next used OntoSem and OntoSem2OWL to support SemNews, an experimental web service that monitors RSS news sources, processes the summaries of the news stories and publishes a structured representation of the meaning of the text in the news story.

BibTeX OWL Tweet Scholar

Tags: information extraction, natural language processing, natural language, semantic web

Type: Article

Volume: 3

Number: 4

Downloads: 3981 downloads

Google Scholar Citations: 13 citations