Multimedia resource summarization

• Publications
  • Judith Klavans and Smaranda Muresan. DEFINDER: Rule-Based Methods for the Extraction of Medical Terminology and Their Assocciated Definitions from On-line Text. In Proc. of 2000 AMIA Annual Symposium. [in press]
  • Hongyan Jing and Kathleen R. McKeown, Cut and paste based text summarization, In Proc. of the First Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL'2000), Seattle, Wa., May 2000.
  • Vassileios Hatzivassiloglou, Olga Merport, Kathleen R. McKeown, and Desmond A. Jordan, Extracting patient profiles from patient records and online literature, In Proc. of the AMIA 1999 Annual Symposium, Wash DC, November 1999.

• Websites
  • Combined Layout and Segmentation Processor(CLASP)
    (http://www.cs.columbia.edu/ min/research/clasp/)
  • Text summarization demo
    (http://www.cs.columbia.edu/diglib/PERSIVAL/text_summarization/)
  • Definition Extraction demo
    (http://www.cs.columbia.edu/ smara/definition_extraction/)
  • Term Identification
    (http://www.cs.columbia.edu/diglib/PERSIVAL/term_identification/)

• Products
  • CLASP - layout + segmentation program that produces document maps (that annotate document topic nesting and logical styles such as headers, captions & tables) from raw ASCII texts.
  • Heading.pm - perl module to deal with the ontological structure of headers and fields for its analysis in the contexts of similar and dissimilar headers across documents.
  • Term Identification - code to identify terms in technical text.
  • DEFINDER - code to identify definitions and the terms they define in lay text.
  • CPS - cut and paste based single document summarization system that produces a generic summary of a single document given as input. Has been applied to medical health news articles.

• Talks
  • Smaranda Muresan and Judith Klavans, Extraction of Definitions and the Terms they Define from On-line Text, internal talk, Columbia PERSIVAL DLI2 Project, April 2000.
  • Noemie Elhadad and Kathleen McKeown, Scenario- Text Summarization Module, internal talk, Columbia PERSIVAL DLI2 Project, January 2000.
  • Vasileios Hatzivassiloglou, Generating Patient Specific Summaries of On-line Literature, internal talk, Columbia PERSIVAL DLI2 Project, September 1999