Abstract. We consider a new discriminative learning approach to sequence labeling based on the statistical concept of the Z-score. Given a training set of pairs of hidden-observed ...
This paper develops an unsupervised discriminant projection (UDP) technique for feature extraction. UDP takes the local and non-local information into account, seeking to find a p...
This work proposes a new approach to the retrieval of images from text queries. Contrasting with previous work, this method relies on a discriminative model: the parameters are sel...
We present a discriminative, latent variable approach to syntactic parsing in which rules exist at multiple scales of refinement. The model is formally a latent variable CRF gramm...
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Brian Roark, Murat Saraclar, Michael Collins, Mark...