Current Research
GovStat
The GovStat Project, (formally
known as Integration of Data and Interfaces to Enhance Human
Understanding
of Government Statistics: Toward the National Statistical Knowledge
Network),
"seeks to create an integrated model of user access to and use of US
government statistical information that is rooted in realistic data models
and innovative user interfaces."
Our project motto is find what you need, understand what you find.
My work on this project focuses on the
Statistical
Interactive Glossary
(SIG), metadata for statistical tasks, and envisioning new
kinds of
help for
supporting users of statistics.
GovStat Papers and
Presentations
Reports
to the Bureau of Labor Statistics
Chief Complaint
When you go to the emergency room, the triage nurse asks why you are
there. The chief complaint data element of your patient
record briefly describes your response.
In collaboration with
Dr. Debbie
Travers, who developed the Emergency Medical Text Processor (EMT-P),
and
Dr. Anna
Waller, both of the
UNC Department
of Emergency Medicine and the
North
Carolina Emergency Department Database (NCEDD), the goal of the Chief
Complaint
Vocabulary Project is to analyse
the form and content of chief complaints, with the eventual goal of
developing a standardized vocabulary.
Natural Language Processing Reading Group
Bryan Heidorn at UIUC and Stephanie Haas at the University of North
Carolina and 2005-2007 Research Fellow at UIUC will be holding a parallel
reading group in Natural Language Processing (NLP). This group will meet
through the Fall semester and perhaps extending into the Spring semester.
In this reading group we will review recent NLP work at UNC and UIUC. Some
meetings will be held via video conference connecting both universities.
The reading group will explore issues in working with sublanguage and
genre for extraction, indexing and markup, and mapping, with the eventual
aim of writing proposals for research projects.
Topics include sublanguages and related topics, including terminology,
genre, and user communities, semi-structured information retrieval and
current and future projects at the two institutions, such as Information
Extraction from natural history texts (e.g. Herbis and BioGeoMancer
projects, UIUC) and government documents (GovStat, UNC).
NLP Reading Group Wiki