Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms Export

@misc{citeulike:1459587, abstract = {We describe new algorithms for training tagging models, as an alternative to maximum-entropy models or conditional random fields (CRFs). The algorithms rely on Viterbi decoding of training examples, combined with simple additive updates. We describe theory justifying the algorithms through a modification of the proof of convergence of the perceptron algorithm for classification problems. We give experimental results on part-of-speech tagging and base noun phrase chunking, in both cases showing...}, author = {Collins, M.}, citeulike-article-id = {1459587}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.6725}, keywords = {discriminative, hidden-variable, hmm}, posted-at = {2007-08-22 16:26:15}, priority = {2}, title = {Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.6725}, year = {2002} }

TY - GEN ID - citeulike:1459587 L3 - citeulike-article-id:1459587 N2 - We describe new algorithms for training tagging models, as an alternative to maximum-entropy models or conditional random fields (CRFs). The algorithms rely on Viterbi decoding of training examples, combined with simple additive updates. We describe theory justifying the algorithms through a modification of the proof of convergence of the perceptron algorithm for classification problems. We give experimental results on part-of-speech tagging and base noun phrase chunking, in both cases showing... TI - Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms KW - discriminative KW - hidden-variable KW - hmm AU - Collins, M PY - 2002/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.18.6725 ER -