One of my projects this fall was to participate in a shared task organized in conjunction with the AMIA conference. The task was to identify is someone was a smoker or not not based on the contents of their medical record.
I pulled a few systems out of my usual bag of tricks and the results of that may be seen here: Determining Smoker Status using Supervised and Unsupervised Learning with Lexical Features (Pedersen) - To Appear in the Working Notes of the i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data, Nov 10-11, 2006, Washington, DC. http://www.d.umn.edu/~tpederse/Pubs/i2b2-2006.pdf The usual bag of tricks includes SenseTools and SenseClusters, and I'm pleased to say both worked pretty well in this rather different domain. More info about the workshop and shared task can be found here: https://www.i2b2.org/NLP/ Enjoy, Ted -- Ted Pedersen http://www.d.umn.edu/~tpederse Yahoo! Groups Links <*> To visit your group on the web, go to: http://groups.yahoo.com/group/nlpatumd/ <*> Your email settings: Individual Email | Traditional <*> To change settings online go to: http://groups.yahoo.com/group/nlpatumd/join (Yahoo! ID required) <*> To change settings via email: mailto:[EMAIL PROTECTED] mailto:[EMAIL PROTECTED] <*> To unsubscribe from this group, send an email to: [EMAIL PROTECTED] <*> Your use of Yahoo! Groups is subject to: http://docs.yahoo.com/info/terms/
