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. Despite progress in Computational Linguistics, pragmatics of human communication remain 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 general information 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 still a challenge for current natural language research. During 1994-2012 Professor Di Marco was the project leader of the HealthDoc Project, which involved researchers from the University of Waterloo, University of Southern California, and the University of Toronto in developing such systems for personalized health education. HealthDoc resulted in two patents (U.S. 2005, Canada 2007) and technology transfer to a U.S. health media company. The original project was funded by the Province of Ontario, with additional funding from Nortel, Bell Canada, and the Natural Sciences and Engineering Research Council of Canada (NSERC).
Professor Di Marco is continuing her work on computational stylistics and rhetoric, with investigation into real-world applications such as sentiment analysis, genre detection, and information extraction.
Professor Di Marco is also developing interests in serious games, particularly games for health, and narrative modeling in games. She is Theme Leader: Games That Change Behaviour for the University of Waterloo Games Institute’s SSHRC-funded IMMERSe project.
Degrees and Awards
BSc, MSc, PhD (Toronto)
Mohammed Alliheedi and Chrysanne DiMarco.
Rhetorical figuration as a metric in text summarization.
Proceedings, 2014 Canadian Artificial Intelligence Conference, May 6-9, 2014, Montreal, QC
G. Ross, C. DiMarco, E. Afros, E. Hovy, A. Malton, A.J. Malton, and M. Skala.
A health rhetorical model for authoring personalized mobile health information.
2011 AAAI Spring Symposium on Artificial Intelligence and Health Communication, March 2011, Stanford, CA
C. DiMarco, E. Afros, E. Hovy, A. Malton, A.J. Malton, G. Ross, and M. Skala.
An authoring tool for creation of tailorable health learning materials.
American Academy on Communication in Healthcare (AACH) Research and Teaching Forum, October 2010, Scottsdale, Arizona
J. Gawryjolek, C. DiMarco, and R. Harris. Automated annotation and visualization of rhetorical figures. 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
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.