BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Biomedical Natural Language Figure Processing - Hong Yu\, Universi
 ty of Wisconsin-Milwaukee
DTSTART:20111018T110000Z
DTEND:20111018T120000Z
UID:TALK34067@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:To date\, most work on biomedical language processing has addr
 essed entity recognition (e.g.\, identifying gene names in text)\, informa
 tion extraction (finding information about very constrained types of relat
 ions between entities\, e.g.\, protein–protein interactions)\, and infor
 mation retrieval (e.g.\, retrieving documents from large text collections)
 \, while largely ignoring the important knowledge represented in figures. 
 Literature incorporates an approximation of 100 million figures.  An intel
 ligent figure search engine will not only assist biocuration and allow ind
 ividual biomedical researcher to access figures more efficiently from full
 -text biomedical articles\, but also is an important step towards automati
 c validations of genome-wide high-throughput predictions. In this talk\, I
  will describe innovative biomedical natural language figure processing (B
 ioNLfP) approaches developed in my lab. BioNLfP semantically associates te
 xt with figures\, ranks figures based on biological importance\, summarize
 s the content of figures\, and evaluates new user-interfaces.  BioNLfP is 
 funded by both National Institutes of Health and Elsevier\, the latter of 
 which allows BioFigureSearch−the implementation of BioNLfP−to access o
 ver 2 million full-text biomedical articles. \n
LOCATION:FW11\, Computer Laboratory
END:VEVENT
END:VCALENDAR