edu.cmu.minorthird.ui
Class Recommended.VPHMMLearner
java.lang.Object
edu.cmu.minorthird.text.learn.AnnotatorLearner
edu.cmu.minorthird.text.learn.AbstractBatchAnnotatorLearner
edu.cmu.minorthird.text.learn.SequenceAnnotatorLearner
edu.cmu.minorthird.ui.Recommended.VPHMMLearner
- Enclosing class:
- Recommended
public static class Recommended.VPHMMLearner
- extends SequenceAnnotatorLearner
Uses the voted perceptron algorithm to learn a parameters of a
hidden Markov model (HMM). This method is similar to a CRF, but
often less expensive to train.
This iterates over the data only 5 times. Subsequent
experiments suggest that iterating 20, 50, or 100 times often
gives better performance.
Reference: Michael Collins, Discriminative Training Methods
for Hidden Markov Models: Theory and Experiments with Perceptron
Algorithms, Empirical Methods in Natural Language Processing (EMNLP),
2002.
Methods inherited from class edu.cmu.minorthird.text.learn.AbstractBatchAnnotatorLearner |
getAnnotationType, getSequenceDataset, getSpanFeatureExtractor, getTaggingReduction, getTaggingReductionHelp, hasNextQuery, nextQuery, reset, setAnnotationType, setAnswer, setDocumentPool, setSpanFeatureExtractor, setTaggingReduction |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Recommended.VPHMMLearner
public Recommended.VPHMMLearner()