SOFIE: A Self-Organizing Framework for Information Extraction

Presented at: 18th International World Wide Web Conference (WWW2009)

by Fabian M. Suchanek, Mauro Sozio, Gerhard Weikum


This paper presents SOFIE, a system for automated on- tology extension. SOFIE can parse natural language docu- ments, extract ontological facts from them and link the facts into an ontology. SOFIE uses logical reasoning on the exist- ing knowledge and on the new knowledge in order to disam- biguate words to their most probable meaning, to reason on the meaning of text patterns and to take into account world knowledge axioms. This allows SOFIE to check the plau- sibility of hypotheses and to avoid inconsistencies with the ontology. The framework of SOFIE unites the paradigms of pattern matching, word sense disambiguation and ontolog- ical reasoning in one unified model. Our experiments show that SOFIE delivers high-quality output, even from unstruc- tured Internet documents.

Keywords: Semantic/Data Web

Resource URI on the dog food server:

Explore this resource elsewhere: