DRCSCS Profile - Chrysanne DiMarco

Professor Di Marco's research focuses on the development of computational models of natural language pragmatics for use in such applications as natural language generation, text analysis, and health informatics. “Pragmatics” are the subtle but significant aspects of language that involve specific choices of words, grammatical form, and deeper semantic content that together contribute to the overall meaning of a text or utterance. In recent years, researchers in Computational Linguistics have begun to produce working systems with real-world utility, but current systems are still able to deal only with restricted, simplified, language. Most systems are still challenged by basic problems associated with analyzing syntax and determining semantic content while the pragmatics of human communication remains understudied and under-represented in current computational systems.

For example, in health informatics, most patient-education material is often limited in its effectiveness by the need to address it to a wide audience. What is generally produced is either a minimal, generic document or a maximal document that tries to provide all the information that might be relevant to someone. Ideally, a Natural Language Generation system could, on demand, customize a “master document” to produce a personalized version specific to the needs of a particular patient. However, building such a system to generate potentially many hundreds, or even thousands, of individually tailored documents is beyond the scope of current natural language research. The goal of “The HealthDocTCDE Project” is to address research issues in Computational Linguistics, Artificial Intelligence, and Health Informatics related to the development of language technologies for personalized multimedia generation.

Professor Di Marco is the project leader of the HealthDocTCDE Project, which began in 1994 at the University of Waterloo, and now involves researchers from the University of Waterloo, the Information Sciences Institute of the University of Southern California, and the University of Toronto. The original project was funded by the Province of Ontario. Current funding is being provided by the Natural Sciences and Engineering Research Council of Canada (NSERC).

Professor Di Marco is the President and CEO of Rhetoritech Persuasive Language Technologies Inc., which was incorporated in Ontario in December 2009. The other Directors of Rhetoritech are Dr. Eduard Hovy of the Information Sciences Institute at the University of Southern California and Vic DiCiccio, Director of the Institute for Computer Research at the University of Waterloo. Rhetoritech's tailoring technology was granted a U.S. patent in 2005 and a Canadian patent in 2007.

Professor Di Marco's research interests also include the emerging field of Biological Natural Language Processing, i.e., the application of Computational Linguistics theory and methods to Information Retrieval and Information Extraction both from large corpora of online biomedical articles and from biological data as well.

Representative Publications

J. Gawryjolek, C. DiMarco, and R. Harris. Automated annotation and visualization of rhetorical figures (system demonstration). 9th International Workshop on Computational Models of Natural Argument, International Joint Conference on Artificial Intelligence (IJCAI) Workshop, July 2009, Pasadena,CA.

Randy Harris and Chrysanne DiMarco. Constructing a rhetorical figuration ontology. Symposium on Persuasive Technology and Digital Behaviour Intervention, Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB), April 2009, Edinburgh, Scotland

Chrysanne DiMarco, David Wiljer, and Eduard Hovy. Self-managed access to personalized healthcare through automated generation of tailored health educational materials from electronic health records (position paper). AAAI Fall Symposium on Virtual Health Interaction, November 2009, Washington DC.

C. DiMarco, P. Bray, H.D. Covvey, D.D. Cowan, V. DiCiccio, E. Hovy, J. Lipa, and C. Yang. Authoring and generation of individualized patient education materials. Journal on Information Technology in Healthcare, 2008.

C. DiMarco, H.D. Covvey, P. Bray, D.D. Cowan, V. DiCiccio, E. Hovy, J. Lipa, and D. Mulholland. The development of a natural language generation system for personalized e-health information. 12th International Health (Medical) Informatics Congress (Medinfo 2007), 2007.

C. DiMarco, P. Bray, H.D. Covvey, D.D. Cowan, V. DiCiccio, E. Hovy, J. Lipa, and C. Yang. Authoring and generation of individualized patient education materials. Conference of the American Medical Informatics Association, 2006.

C. DiMarco and R.E. Mercer. Hedging in scientific articles as a means of classifying citations. Computing attitude and affect in text: Theory and applications, James G. Shanahan, Yan Qu, Janyce Wiebe (Editors), Springer-Verlag, 2005.

X. He and C. DiMarco, Using lexical chaining to rank protein-protein interactions in biomedical texts. BioLink 2005: Workshop on Linking Biological Literature, Ontologies and Databases: Mining Biological Semantics, Conference of the Association for Computational Linguistics, (poster), 2005.

R.E. Mercer, C. DiMarco, and F. Kroon, The frequency of hedging cues in citation contexts in scientific writing. Proceedings of the Conference of the Canadian Society for the Computational Studies of Intelligence (CSCSI), 2004.

R.E. Mercer and C. DiMarco. The importance of fine-grained cue phrases in scientific citations. Proceedings of the Conference of the Canadian Society for the Computational Studies of Intelligence (CSCSI), 2003.

David R. Cheriton School of Computer Science
University of Waterloo
Waterloo, Ontario, Canada N2L 3G1

Tel: 519-888-4567 x33293
Fax: 519-885-1208

Contact | Feedback: cs-webmaster@cs.uwaterloo.ca | David R. Cheriton School of Computer Science | Faculty of Mathematics

Last modified: Monday, 20-Dec-2010 14:29:43 EST

Menu:Show Hide

Research Interests

Representative Publications