edu.cmu.minorthird.text.learn
Class ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE

java.lang.Object
  edu.cmu.minorthird.text.learn.SpanFE
      edu.cmu.minorthird.text.learn.SampleFE.AnnotatedSpanFE
          edu.cmu.minorthird.text.learn.SampleFE.ExtractionFE
              edu.cmu.minorthird.text.learn.ConditionalSemiMarkovModel.CSMMSpanFE
                  edu.cmu.minorthird.text.learn.ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE

All Implemented Interfaces:

MixupCompatible, SpanFeatureExtractor, java.io.Serializable

Enclosing class:

ConditionalSemiMarkovModel

public static class ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE
extends ConditionalSemiMarkovModel.CSMMSpanFE

Feature extractor for providing distance-based features on terms. Dictionary can be specified either as an external file or by using the training spans. - Sunita Sarawagi

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class edu.cmu.minorthird.text.learn.SpanFE

SpanFE.Filter, SpanFE.Function, SpanFE.Result, SpanFE.SetResult<T>, SpanFE.SpanResult, SpanFE.SpanSetResult, SpanFE.StringBagResult, SpanFE.TokenSetResult

Field Summary

Fields inherited from class edu.cmu.minorthird.text.learn.SampleFE.ExtractionFE

tokenPropertyFeatures, useCharType, useCompressedCharType, windowSize

Fields inherited from class edu.cmu.minorthird.text.learn.SpanFE

annotatorLoader, instance, requiredAnnotation, requiredAnnotationFileToLoad, STORE_AS_BINARY, STORE_AS_COUNTS, STORE_COMPACTLY

Constructor Summary

ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE(java.lang.String dictionaryFile, java.lang.String distanceNames)

ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE(java.lang.String dictionaryFile, java.lang.String distanceNames, boolean addTraining, boolean useCrossValArg)

Method Summary

void	extractFeatures(TextLabels labels, Span span) Implement this with a specific set of SpanFE 'pipelines'.
void	train(java.util.Iterator<AnnotationExample> iter)
void	trainDistances()

Methods inherited from class edu.cmu.minorthird.text.learn.ConditionalSemiMarkovModel.CSMMSpanFE

extractFeatures

Methods inherited from class edu.cmu.minorthird.text.learn.SampleFE.ExtractionFE

getFeatureWindowSize, getTokenPropertyFeatures, getUseCharType, getUseCompressedCharType, setFeatureWindowSize, setTokenPropertyFeatures, setTokenPropertyFeatures, setUseCharType, setUseCompressedCharType

Methods inherited from class edu.cmu.minorthird.text.learn.SpanFE

emit, emit, emit, emit, extractInstance, extractInstance, from, from, getAnnotationProvider, getRequiredAnnotation, requireMyAnnotation, setAnnotationProvider, setAnnotatorLoader, setFeatureStoragePolicy, setRequiredAnnotation, setRequiredAnnotation, trace

Methods inherited from class java.lang.Object

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

Constructor Detail

ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE

public ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE(java.lang.String dictionaryFile,
                                                           java.lang.String distanceNames)

ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE

public ConditionalSemiMarkovModel.CSMMWithDictionarySpanFE(java.lang.String dictionaryFile,
                                                           java.lang.String distanceNames,
                                                           boolean addTraining,
                                                           boolean useCrossValArg)

Method Detail

trainDistances

public void trainDistances()

train

public void train(java.util.Iterator<AnnotationExample> iter)

extractFeatures

public void extractFeatures(TextLabels labels,
                            Span span)

Description copied from class: SpanFE

Implement this with a specific set of SpanFE 'pipelines'. Each pipeline will typically start with 'start(span)' and end with 'emit()'.

Overrides:

extractFeatures in class ConditionalSemiMarkovModel.CSMMSpanFE