cc.mallet.fst.confidence
Class GammaAverageConfidenceEstimator

java.lang.Object
  extended by cc.mallet.fst.confidence.TransducerConfidenceEstimator
      extended by cc.mallet.fst.confidence.GammaAverageConfidenceEstimator
All Implemented Interfaces:
java.io.Serializable

public class GammaAverageConfidenceEstimator
extends TransducerConfidenceEstimator

Calculates the confidence in an extracted segment by taking the average of P(s_i|o) for each state in the segment.

See Also:
Serialized Form

Field Summary
 
Fields inherited from class cc.mallet.fst.confidence.TransducerConfidenceEstimator
model
 
Constructor Summary
GammaAverageConfidenceEstimator(Transducer model)
           
 
Method Summary
 double estimateConfidenceFor(Segment segment, SumLatticeDefault cachedLattice)
          Calculates the confidence in the tagging of a Segment.
 
Methods inherited from class cc.mallet.fst.confidence.TransducerConfidenceEstimator
estimateConfidenceFor, getSegmentConfidences, getTransducer, rankSegmentsByConfidence, rankSegmentsByConfidence
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

GammaAverageConfidenceEstimator

public GammaAverageConfidenceEstimator(Transducer model)
Method Detail

estimateConfidenceFor

public double estimateConfidenceFor(Segment segment,
                                    SumLatticeDefault cachedLattice)
Calculates the confidence in the tagging of a Segment.

Specified by:
estimateConfidenceFor in class TransducerConfidenceEstimator
Returns:
0-1 confidence value. higher = more confident.