BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Conditional Random Fields : Theory and Application - Matt Seigel (
 University of Cambridge)
DTSTART:20100603T130000Z
DTEND:20100603T143000Z
UID:TALK24005@talks.cam.ac.uk
CONTACT:Shakir Mohamed
DESCRIPTION:Conditional Random Fields are a probabilistic framework for la
 belling and segmentation of structured data\, such as sequences. The core 
 principal of such models is to define a conditional probability distributi
 on over label sequences as opposed to a joint distribution over label and 
 observation sequences (which is the approach taken using Hidden Markov Mod
 els). This approach is able to circumvent many of the issues typically enc
 ountered when using HMMs and other sequential models. In most applications
  across a diverse list of fields\, CRFs have been found to outperform clas
 sical sequential models.\n\nThis talk aims to serve as an introduction to 
 CRF models\, while covering some of the details of the implementation of s
 uch models and discussing their application. A theoretical motivation for 
 such models will firstly be presented. Thereafter\, specific topics relati
 ng to design\, training and implementation of CRFs will be discussed.\n\nT
 he following resources may be useful:\n\n"J. Lafferty\, A. McCallum and F.
  Pereira\, Conditional random fields: Probabilistic models for segmenting 
 and labeling sequence data\, In Proc. 18th International Conf. on Machine 
 Learning\, Morgan Kaufmann\, San Francisco\, CA (2001) 282–289":http://w
 ww.cis.upenn.edu/~pereira/papers/crf.pdf\n\n"R. Klinger and K. Tomanek\, C
 lassical Probabilistic Models and Conditional Random Fields\, Algorithm En
 gineering Report TR07-2-013\, Department of Computer Science\, Dortmund Un
 iversity of Technology\, December 2007. ISSN 1864-4503":http://www.scai.fr
 aunhofer.de/fileadmin/images/bio/data_mining/paper/crf_klinger_tomanek.pdf
 \n\n"C. Sutton and A. McCallum\, An Introduction to Conditional Random Fie
 lds for Relational Learning\, In Introduction to Statistical Relational Le
 arning\, Edited by Lise Getoor and Ben Taskar. MIT Press (2006)":http://ww
 w.cs.umass.edu/~mccallum/papers/crf-tutorial.pdf
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR