Issue No. 08 - August (2008 vol. 30)
Extending traditional models for discriminative labeling of structured data to include higher-order structure in the labels results in an undesirable exponential increase in model complexity. In this paper, we present a model that is capable of learning such structures using a random field of parameterized features. These features can be functions of arbitrary combinations of observations, labels and auxiliary hidden variables. We also present a simple induction scheme to learn these features, which can automatically determine the complexity needed for a given data set. We apply the model to two real-world tasks, information extraction and image labeling, and compare our results to several other methods for discriminative labeling.
machine learning, statistical models, induction, text analysis, pixel classification, markov random fields
Liam Stewart, Richard S. Zemel, Xuming He, "Learning Flexible Features for Conditional Random Fields", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 30, no. , pp. 1415-1426, August 2008, doi:10.1109/TPAMI.2007.70790