Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Semi-supervised conditional random fields for improved sequence segmentation and labeling
ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
MMR-based active machine learning for bio named entity recognition
NAACL-Short '06 Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers
Efficient computation of the hidden Markov model entropy for a given observation sequence
IEEE Transactions on Information Theory
An analysis of active learning strategies for sequence labeling tasks
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Active learning for part-of-speech tagging: accelerating corpus annotation
LAW '07 Proceedings of the Linguistic Annotation Workshop
Aspects of semi-supervised and active learning in conditional random fields
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part III
Mining query structure from click data: a case study of product queries
Proceedings of the 20th ACM international conference on Information and knowledge management
A weakly-supervised approach to argumentative zoning of scientific documents
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
Entropy regularization is a straightforward and successful method of semi-supervised learning that augments the traditional conditional likelihood objective function with an additional term that aims to minimize the predicted label entropy on unlabeled data. It has previously been demonstrated to provide positive results in linear-chain CRFs, but the published method for calculating the entropy gradient requires significantly more computation than supervised CRF training. This paper presents a new derivation and dynamic program for calculating the entropy gradient that is significantly more efficient---having the same asymptotic time complexity as supervised CRF training. We also present efficient generalizations of this method for calculating the label entropy of all sub-sequences, which is useful for active learning, among other applications.