edu.umass.cs.mallet.base.fst.confidence
Class TransducerConfidenceEstimator

java.lang.Object
  edu.umass.cs.mallet.base.fst.confidence.TransducerConfidenceEstimator

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

ConstrainedForwardBackwardConfidenceEstimator, GammaAverageConfidenceEstimator, GammaProductConfidenceEstimator, MaxEntConfidenceEstimator, RandomConfidenceEstimator

public abstract class TransducerConfidenceEstimator

extends java.lang.Object

implements java.io.Serializable

Abstract class that estimates the confidence of a Segment extracted by a Transducer.

See Also:

Serialized Form

Constructor Summary

TransducerConfidenceEstimator()

Method Summary

double	estimateConfidenceFor(Segment segment) Calculates the confidence in the tagging of a Segment.
abstract double	estimateConfidenceFor(Segment segment, Transducer.Lattice lattice)
java.util.Vector	getSegmentConfidences()
Transducer	getTransducer()
Segment[]	rankSegmentsByConfidence(InstanceList ilist, java.lang.Object[] startTags, java.lang.Object[] continueTags) Ranks all Segments in this InstanceList by confidence estimate.
Segment[]	rankSegmentsByConfidence(Instance instance, java.lang.Object[] startTags, java.lang.Object[] continueTags) ranks the segments in one Instance

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

TransducerConfidenceEstimator

public TransducerConfidenceEstimator()

Method Detail

estimateConfidenceFor

public double estimateConfidenceFor(Segment segment)

Calculates the confidence in the tagging of a Segment.

estimateConfidenceFor

public abstract double estimateConfidenceFor(Segment segment,
                                             Transducer.Lattice lattice)

getSegmentConfidences

public java.util.Vector getSegmentConfidences()

rankSegmentsByConfidence

public Segment[] rankSegmentsByConfidence(InstanceList ilist,
                                          java.lang.Object[] startTags,
                                          java.lang.Object[] continueTags)

Ranks all Segments in this InstanceList by confidence estimate.

Parameters:

ilist - list of segmentation instances

startTags - represent the labels for the start states (B-) of all segments

continueTags - represent the labels for the continue state (I-) of all segments

Returns:

array of Segments ordered by non-decreasing confidence scores, as calculated by estimateConfidenceFor

rankSegmentsByConfidence

public Segment[] rankSegmentsByConfidence(Instance instance,
                                          java.lang.Object[] startTags,
                                          java.lang.Object[] continueTags)

ranks the segments in one Instance

Parameters:

instance - instances to be segmented

startTags - represent the labels for the start states (e.g. B-) of all segments

continueTags - represent the labels for the continue state (e.g. I-) of all segments

Returns:

array of Segments ordered by non-decreasing confidence scores, as calculated by estimateConfidenceFor

getTransducer

public Transducer getTransducer()