Component Services for UIMA-based Knowledge Integration (SUKI)

An important application of text (or multi-modal) analytics is to produce formal representations of discovered content to support knowledge-based reasoning. For example, such applications may need to construct an OWL (Web Ontology Language) knowledge base from the results captured in a stream of CASes by a UIMA analysis pipeline.

SUKI is a set of component services designed to enable transforming the results of UIMA analysis into knowledge representations suitable for formal reasoning and processing by widely available knowledge base and semantic web tools like Protégé and Jena.

Research Contact(s): Dr. David Ferrucci ferrucci@us.ibm.com

SUKI Overview Paper:

• Overview of Component Services for Knowledge Integration in UIMA (a.k.a. SUKI). David Ferrucci, J. William Murdock, and Christopher Welty. IBM Research Report RC24074. 2006.

Additional Related Papers:

Knowledge Integration

• Towards Knowledge Acquisition from Information Extraction. Christopher Welty and J. William Murdock. Proceedings of the 5th International Semantic Web Conference (ISWC'06), Athens, GA. 2006.
• Obtaining Formal Knowledge from Informal Text Analysis. J. William Murdock and Christopher Welty. IBM Research Report RC23961. 2006.

Provenance

• Text Analysis as Formal Inference for the Purposes of Uniform Tracing and Explanation Generation. David Ferrucci. IBM Research Technical Report RC23372. 2004.
• Explaining Conclusions from Diverse Knowledge Sources. J. William Murdock, Deborah L. McGuinness, Paulo Pinheiro da Silva, Christopher Welty, and David Ferrucci. Proceedings of the 5th International Semantic Web Conference (ISWC'06), Athens, GA. 2006.
• Encoding Extraction as Inferences. J. William Murdock, Paulo Pinheiro da Silva, David Ferrucci, Christopher Welty, and Deborah L. McGuinness. In Proceedings of AAAI Spring Symposium on Metacognition on Computation, AAAI Press, Stanford University, USA, pages 92-97, 2005.
• Tracking Information Extraction from Intelligence Documents. Christopher Welty, J. William Murdock, Paulo Pinheiro da Silva, Deborah L. McGuinness, David Ferrucci, and Richard Fikes. Proceedings of the 2005 International Conference on Intelligence Analysis (IA 2005), McLean, VA, USA, 2-6 May, 2005.

Knowledge-Level Representation of Extraction Results

• The Semantics of Multiple Annotations. Christopher Welty and J. William Murdock. IBM Research Technical Report RC22979.

SUKI-driven Search

• The Semantic Analysis Workbench (SAW): Towards a Framework for Knowledge Gathering and Synthesis. Anthony Levas, Eric Brown, J. William Murdock, and David Ferrucci. Proceedings of the International Conference on Intelligence Analysis. McClean, VA, May 2-6, 2005.