Conditional Random Fields Representation Probabilistic Graphical Models Markov Networks Conditional Random Fields

Task-specific prediction X Y Image segmentation Text processing

Correlated Features Ci Xi1 ... Xik color & texture histograms

CRF Representation

CRFs and Logistic Model draw structure, show conditional distribution

CRFs for Language Features: word capitalized, word in atlas or name list, previous word is “Mrs”, next word is “Times”, …

More CRFs for Language Different chains can use different features

Summary A CRF is parameterized the same as a Gibbs distribution, but normalized differently Generalizes logistic regression models Don’t need to model distribution over variables we don’t care about Allows models with highly expressive features, without worrying about wrong independencies

END END END