| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
TextSliceExtractor.extract(JCas view,
T focusAnnotation) |
List<Feature> |
FilteringExtractor.extract(JCas view,
T focusAnnotation) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
SyntacticFirstChildOfGrandparentOfLeafExtractor.extract(JCas view,
T focusAnnotation) |
List<Feature> |
SubCategorizationExtractor.extract(JCas jCas,
TreebankNode node) |
List<Feature> |
SiblingExtractor.extract(JCas jCas,
TreebankNode node) |
List<Feature> |
ParentExtractor.extract(JCas jCas,
TreebankNode node) |
List<Feature> |
HeadWordExtractor.extract(JCas jCas,
TreebankNode constituent) |
List<Feature> |
TargetPathExtractor.extract(JCas jCas,
TreebankNode source,
TreebankNode target) |
List<Feature> |
SyntacticPathExtractor.extract(JCas view,
TreebankNode leftConstituent,
TreebankNode rightConstituent)
Extract a string representation of a path feature.
|
List<Feature> |
SyntacticLeafToLeafPathPartsExtractor.extract(JCas jCas,
T source,
U target) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
TokenTextForSelectedPosExtractor.extract(JCas view,
Token token) |
| Modifier and Type | Class and Description |
|---|---|
class |
TreeFeature
Copyright (c) 2007-2008, Regents of the University of Colorado All rights reserved. |
| Modifier and Type | Method and Description |
|---|---|
static Feature |
Feature.createFeature(String namePrefix,
Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
Instance.getFeatures()
Get the list of features for this instance.
|
| Modifier and Type | Method and Description |
|---|---|
void |
Instance.add(Feature feature)
Add a feature to the instance.
|
static Feature |
Feature.createFeature(String namePrefix,
Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
void |
Instance.addAll(Collection<Feature> feats)
Add a collection of features to the instance.
|
OUTCOME_TYPE |
Classifier.classify(List<Feature> features)
Classifies a list of features.
|
List<OUTCOME_TYPE> |
SequenceClassifier.classify(List<List<Feature>> features)
Classifies a sequence of feature lists.
|
Map<OUTCOME_TYPE,Double> |
Classifier.score(List<Feature> features)
Classify a list of features, and return the scores for each of the outcomes
|
List<Map<OUTCOME_TYPE,Double>> |
SequenceClassifier.score(List<List<Feature>> features)
Classify a sequence of feature lists, and return the scores for each of the outcomes for each
feature list.
|
static <OUTCOME_TYPE> |
Instances.toInstances(List<OUTCOME_TYPE> outcomes,
List<List<Feature>> featureLists)
Create a list of Instances from a list of outcomes and a list of feature-lists.
|
| Constructor and Description |
|---|
Instance(Collection<Feature> features) |
Instance(OUTCOME_TYPE outcome,
Collection<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
OUTCOME_TYPE |
SingleOutcomeClassifier.classify(List<Feature> features) |
Map<OUTCOME_TYPE,Double> |
SingleOutcomeClassifier.score(List<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
static CleartkEncoderException |
CleartkEncoderException.noMatchingEncoder(Feature feature,
List<? extends FeatureEncoder<?>> encoders) |
| Modifier and Type | Method and Description |
|---|---|
List<NameNumber> |
StringEncoder.encode(Feature feature) |
List<NameNumber> |
NumberEncoder.encode(Feature feature) |
List<NameNumber> |
MultiBagEncoder.encode(Feature feature) |
List<ENCODED_TYPE> |
FeatureEncoderChain.encode(Feature feature) |
List<T> |
FeatureEncoder.encode(Feature feature) |
List<NameNumber> |
FeatureCollectionEncoder.encode(Feature feature) |
List<NameNumber> |
BooleanEncoder.encode(Feature feature) |
List<NameNumber> |
BagEncoder.encode(Feature feature) |
boolean |
StringEncoder.encodes(Feature feature) |
boolean |
NumberEncoder.encodes(Feature feature) |
boolean |
MultiBagEncoder.encodes(Feature feature) |
boolean |
FeatureEncoderChain.encodes(Feature feature) |
boolean |
FeatureEncoder.encodes(Feature feature) |
boolean |
FeatureCollectionEncoder.encodes(Feature feature) |
boolean |
BooleanEncoder.encodes(Feature feature) |
boolean |
BagEncoder.encodes(Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
List<NameNumber> |
NameNumberFeaturesEncoder.encodeAll(Iterable<Feature> features) |
ENCODED_FEATURES_TYPE |
FeaturesEncoder.encodeAll(Iterable<Feature> features) |
FeatureVector |
FeatureVectorFeaturesEncoder.encodeAll(Iterable<Feature> features) |
| Modifier and Type | Class and Description |
|---|---|
class |
TypePathFeature
Copyright (c) 2007-2008, Regents of the University of Colorado All rights reserved. |
| Modifier and Type | Method and Description |
|---|---|
Collection<Feature> |
FeatureCollection.getFeatures() |
| Constructor and Description |
|---|
FeatureCollection(Collection<Feature> features) |
FeatureCollection(String identifier,
Collection<Feature> features) |
| Modifier and Type | Class and Description |
|---|---|
static class |
CleartkExtractor.NestedCountFeature |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
WhiteSpaceExtractor.extract(JCas view,
Annotation focusAnnotation) |
List<Feature> |
TypePathExtractor.extract(JCas view,
Annotation focusAnnotation) |
List<Feature> |
CoveredTextExtractor.extract(JCas jCas,
Annotation focusAnnotation) |
List<Feature> |
DistanceExtractor.extract(JCas jCas,
Annotation annotation1,
Annotation annotation2) |
List<Feature> |
DirectedDistanceExtractor.extract(JCas jCas,
Annotation annotation1,
Annotation annotation2) |
<SEARCH_T extends Annotation> |
CleartkExtractor.Context.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor)
Extracts features in the given context.
|
<SEARCH_T extends Annotation> |
CleartkExtractor.Focus.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor) |
<SEARCH_T extends Annotation> |
CleartkExtractor.Covered.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor) |
<SEARCH_T extends Annotation> |
CleartkExtractor.Bag.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor) |
<SEARCH_T extends Annotation> |
CleartkExtractor.Count.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor)
This method got a bit gnarly in order to support nested Count contexts.
|
<SEARCH_T extends Annotation> |
CleartkExtractor.Ngram.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor) |
<SEARCH_T extends Annotation> |
CleartkExtractor.Ngrams.extract(JCas jCas,
Annotation focusAnnotation,
CleartkExtractor.Bounds bounds,
Class<SEARCH_T> annotationClass,
FeatureExtractor1<SEARCH_T> extractor) |
List<Feature> |
CleartkExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
List<Feature> |
CleartkExtractor.extract(JCas view,
FOCUS_T annotation1,
FOCUS_T annotation2) |
List<Feature> |
NamingExtractor1.extract(JCas view,
T focusAnnotation) |
List<Feature> |
FeatureExtractor1.extract(JCas view,
T focusAnnotation)
Some feature extractors will require some specific number of annotations that is greater than
one.
|
List<Feature> |
CombinedExtractor1.extract(JCas view,
T focusAnnotation)
Extract features from the Annotation using the sub-extractors.
|
List<Feature> |
RelativePositionExtractor.extract(JCas view,
T annotation1,
U annotation2) |
List<Feature> |
FeatureExtractor2.extract(JCas view,
T annotation1,
U annotation2) |
List<Feature> |
CleartkExtractor.extractBetween(JCas view,
FOCUS_T annotation1,
FOCUS_T annotation2) |
List<Feature> |
CleartkExtractor.extractWithin(JCas view,
FOCUS_T focusAnnotation,
Annotation boundsAnnotation)
Extract features from the annotations around the focus annotation and within the given bounds.
|
| Constructor and Description |
|---|
CleartkExtractor.NestedCountFeature(String baseName,
Feature feature,
Object countedValue) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
NumericTypeFeatureFunction.apply(Feature feature)
If the value of the feature is a StringValue and is determined to be one of DIGITS,
YEAR_DIGITS, ALPHANUMERIC, SOME_DIGITS, or ROMAN_NUMERAL, then a feature containing one of
those five values is returned.
|
List<Feature> |
LowerCaseFeatureFunction.apply(Feature feature) |
List<Feature> |
ContainsHyphenFeatureFunction.apply(Feature feature) |
List<Feature> |
CharacterNgramFeatureFunction.apply(Feature feature) |
List<Feature> |
CharacterCategoryPatternFunction.apply(Feature feature) |
List<Feature> |
CapitalTypeFeatureFunction.apply(Feature feature)
If the value of the feature is a StringValue and is determined to be one of ALL_UPPERCASE,
ALL_LOWERCASE, INITIAL_UPPERCASE, or MIXED_CASE, then a new feature containing one of those
four values is returned.
|
static List<Feature> |
FeatureFunctionExtractor.apply(Function<Feature,List<Feature>> featureFunction,
List<Feature> features) |
List<Feature> |
FeatureFunctionExtractor.extract(JCas jCas,
T focusAnnotation) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
NumericTypeFeatureFunction.apply(Feature feature)
If the value of the feature is a StringValue and is determined to be one of DIGITS,
YEAR_DIGITS, ALPHANUMERIC, SOME_DIGITS, or ROMAN_NUMERAL, then a feature containing one of
those five values is returned.
|
List<Feature> |
LowerCaseFeatureFunction.apply(Feature feature) |
List<Feature> |
ContainsHyphenFeatureFunction.apply(Feature feature) |
List<Feature> |
CharacterNgramFeatureFunction.apply(Feature feature) |
List<Feature> |
CharacterCategoryPatternFunction.apply(Feature feature) |
List<Feature> |
CapitalTypeFeatureFunction.apply(Feature feature)
If the value of the feature is a StringValue and is determined to be one of ALL_UPPERCASE,
ALL_LOWERCASE, INITIAL_UPPERCASE, or MIXED_CASE, then a new feature containing one of those
four values is returned.
|
| Modifier and Type | Method and Description |
|---|---|
static List<Feature> |
FeatureFunctionExtractor.apply(Function<Feature,List<Feature>> featureFunction,
List<Feature> features) |
static List<Feature> |
FeatureFunctionExtractor.apply(Function<Feature,List<Feature>> featureFunction,
List<Feature> features) |
static List<Feature> |
FeatureFunctionExtractor.apply(Function<Feature,List<Feature>> featureFunction,
List<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
MutualInformationFeatureSelectionExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
| Modifier and Type | Method and Description |
|---|---|
boolean |
MutualInformationFeatureSelectionExtractor.apply(Feature feature) |
String |
MutualInformationFeatureSelectionExtractor.nameFeature(Feature feature) |
| Modifier and Type | Class and Description |
|---|---|
class |
TransformableFeature
Abstract base class for transformable features.
|
| Modifier and Type | Field and Description |
|---|---|
protected List<Feature> |
TransformableFeature.features |
| Modifier and Type | Method and Description |
|---|---|
protected abstract Feature |
OneToOneTrainableExtractor_ImplBase.transform(Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
TransformableFeature.getFeatures() |
| Modifier and Type | Method and Description |
|---|---|
protected boolean |
TrainableExtractor_ImplBase.isTransformable(Feature feature) |
protected boolean |
OneToOneTrainableExtractor_ImplBase.isTransformable(Feature feature) |
protected abstract Feature |
OneToOneTrainableExtractor_ImplBase.transform(Feature feature) |
| Constructor and Description |
|---|
TransformableFeature(String name,
List<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
protected Feature |
ZeroMeanUnitStddevExtractor.transform(Feature feature) |
protected Feature |
TfidfExtractor.transform(Feature feature) |
protected Feature |
MinMaxNormalizationExtractor.transform(Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
ZeroMeanUnitStddevExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
List<Feature> |
TfidfExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
List<Feature> |
MinMaxNormalizationExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
List<Feature> |
CentroidTfidfSimilarityExtractor.extract(JCas view,
FOCUS_T focusAnnotation) |
| Modifier and Type | Method and Description |
|---|---|
protected Feature |
ZeroMeanUnitStddevExtractor.transform(Feature feature) |
protected Feature |
TfidfExtractor.transform(Feature feature) |
protected Feature |
MinMaxNormalizationExtractor.transform(Feature feature) |
| Modifier and Type | Method and Description |
|---|---|
Map<String,Double> |
CentroidTfidfSimilarityExtractor.featuresToFeatureMap(List<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
Map<OUTCOME_TYPE,Double> |
Classifier_ImplBase.score(List<Feature> features) |
List<Map<OUTCOME_TYPE,Double>> |
SequenceClassifier_ImplBase.score(List<List<Feature>> features) |
| Modifier and Type | Method and Description |
|---|---|
OUTCOME_TYPE |
GenericLibLinearClassifier.classify(List<Feature> features) |
Map<OUTCOME_TYPE,Double> |
GenericLibLinearClassifier.score(List<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
de.bwaldvogel.liblinear.FeatureNode[] |
FeatureNodeArrayEncoder.encodeAll(Iterable<Feature> features) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
OutcomeFeatureExtractor.extractFeatures(List<Object> previousOutcomes) |
List<Feature> |
DefaultOutcomeFeatureExtractor.extractFeatures(List<Object> previousOutcomes) |
| Modifier and Type | Method and Description |
|---|---|
List<OUTCOME_TYPE> |
ViterbiClassifier.classify(List<List<Feature>> features) |
List<Map<OUTCOME_TYPE,Double>> |
ViterbiClassifier.score(List<List<Feature>> features) |
List<OUTCOME_TYPE> |
ViterbiClassifier.viterbi(List<List<Feature>> featureLists)
This implementation of Viterbi requires at most stackSize * sequenceLength calls to the
classifier.
|
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
TimeWordsExtractor.extract(JCas view,
T focusAnnotation) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
PosFeatureExtractor.extractFeatures(JCas jCas,
TOKEN_TYPE token,
SENTENCE_TYPE sentence) |
| Modifier and Type | Method and Description |
|---|---|
List<Feature> |
DefaultFeatureExtractor.extractFeatures(JCas jCas,
Token token,
Sentence sentence) |
Copyright © 2014. All rights reserved.