gate.creole
Class POSTagger

java.lang.Object
  gate.util.AbstractFeatureBearer
      gate.creole.AbstractResource
          gate.creole.AbstractProcessingResource
              gate.creole.AbstractLanguageAnalyser
                  gate.creole.POSTagger

All Implemented Interfaces:

ANNIEConstants, Executable, LanguageAnalyser, ProcessingResource, Resource, FeatureBearer, NameBearer, Serializable

@CreoleResource(name="ANNIE POS Tagger",
                helpURL="http://gate.ac.uk/userguide/sec:annie:tagger",
                comment="Mark Hepple\'s Brill-style POS tagger")
public class POSTagger
extends AbstractLanguageAnalyser

This class is a wrapper for HepTag, Mark Hepple's POS tagger.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class gate.creole.AbstractProcessingResource

AbstractProcessingResource.InternalStatusListener, AbstractProcessingResource.IntervalProgressListener

Field Summary

static String	BASE_SENTENCE_ANNOTATION_TYPE_PARAMETER_NAME
static String	BASE_TOKEN_ANNOTATION_TYPE_PARAMETER_NAME
protected Boolean	failOnMissingInputAnnotations
protected org.apache.log4j.Logger	logger
static String	OUTPUT_ANNOTATION_TYPE_PARAMETER_NAME
static String	TAG_DOCUMENT_PARAMETER_NAME
static String	TAG_ENCODING_PARAMETER_NAME
static String	TAG_INPUT_AS_PARAMETER_NAME
static String	TAG_LEXICON_URL_PARAMETER_NAME
static String	TAG_OUTPUT_AS_PARAMETER_NAME
static String	TAG_RULES_URL_PARAMETER_NAME
protected POSTagger	tagger

Fields inherited from class gate.creole.AbstractLanguageAnalyser

corpus, document

Fields inherited from class gate.creole.AbstractProcessingResource

interrupted

Fields inherited from class gate.creole.AbstractResource

name

Fields inherited from class gate.util.AbstractFeatureBearer

features

Fields inherited from interface gate.creole.ANNIEConstants

ANNOTATION_COREF_FEATURE_NAME, DATE_ANNOTATION_TYPE, DATE_POSTED_ANNOTATION_TYPE, DEFAULT_FILE, DOCUMENT_COREF_FEATURE_NAME, JOB_ID_ANNOTATION_TYPE, LOCATION_ANNOTATION_TYPE, LOOKUP_ANNOTATION_TYPE, LOOKUP_CLASS_FEATURE_NAME, LOOKUP_INSTANCE_FEATURE_NAME, LOOKUP_LANGUAGE_FEATURE_NAME, LOOKUP_MAJOR_TYPE_FEATURE_NAME, LOOKUP_MINOR_TYPE_FEATURE_NAME, LOOKUP_ONTOLOGY_FEATURE_NAME, MONEY_ANNOTATION_TYPE, ORGANIZATION_ANNOTATION_TYPE, PERSON_ANNOTATION_TYPE, PERSON_GENDER_FEATURE_NAME, PLUGIN_DIR, PR_NAMES, SENTENCE_ANNOTATION_TYPE, SPACE_TOKEN_ANNOTATION_TYPE, TOKEN_ANNOTATION_TYPE, TOKEN_CATEGORY_FEATURE_NAME, TOKEN_KIND_FEATURE_NAME, TOKEN_LENGTH_FEATURE_NAME, TOKEN_ORTH_FEATURE_NAME, TOKEN_STRING_FEATURE_NAME

Constructor Summary

POSTagger()

Method Summary

protected void	addFeatures(Annotation annot, String featureName, String featureValue)
void	execute() Run the resource.
String	getBaseSentenceAnnotationType()
String	getBaseTokenAnnotationType()
String	getEncoding()
Boolean	getFailOnMissingInputAnnotations()
String	getInputASName()
URL	getLexiconURL()
String	getOutputAnnotationType()
String	getOutputASName()
URL	getRulesURL()
Resource	init() Initialise this resource, and return it.
void	setBaseSentenceAnnotationType(String baseSentenceAnnotationtype)
void	setBaseTokenAnnotationType(String baseTokenAnnotationType)
void	setEncoding(String encoding)
void	setFailOnMissingInputAnnotations(Boolean fail)
void	setInputASName(String newInputASName)
void	setLexiconURL(URL newLexiconURL)
void	setOutputAnnotationType(String outputAnnotationType)
void	setOutputASName(String outputASName)
void	setRulesURL(URL newRulesURL)

Methods inherited from class gate.creole.AbstractLanguageAnalyser

getCorpus, getDocument, setCorpus, setDocument

Methods inherited from class gate.creole.AbstractProcessingResource

addProgressListener, addStatusListener, cleanup, fireProcessFinished, fireProgressChanged, fireStatusChanged, getRuntimeParameterValues, getRuntimeParameterValues, interrupt, isInterrupted, reInit, removeProgressListener, removeStatusListener

Methods inherited from class gate.creole.AbstractResource

checkParameterValues, getBeanInfo, getInitParameterValues, getInitParameterValues, getName, getParameterValue, getParameterValue, getParameterValues, removeResourceListeners, setName, setParameterValue, setParameterValue, setParameterValues, setParameterValues, setResourceListeners

Methods inherited from class gate.util.AbstractFeatureBearer

getFeatures, setFeatures

Methods inherited from class java.lang.Object

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

Methods inherited from interface gate.ProcessingResource

reInit

Methods inherited from interface gate.Resource

cleanup, getParameterValue, setParameterValue, setParameterValues

Methods inherited from interface gate.util.FeatureBearer

getFeatures, setFeatures

Methods inherited from interface gate.util.NameBearer

getName, setName

Methods inherited from interface gate.Executable

interrupt, isInterrupted

Field Detail

TAG_DOCUMENT_PARAMETER_NAME

public static final String TAG_DOCUMENT_PARAMETER_NAME

See Also:

Constant Field Values

TAG_INPUT_AS_PARAMETER_NAME

public static final String TAG_INPUT_AS_PARAMETER_NAME

See Also:

Constant Field Values

TAG_LEXICON_URL_PARAMETER_NAME

public static final String TAG_LEXICON_URL_PARAMETER_NAME

See Also:

Constant Field Values

TAG_RULES_URL_PARAMETER_NAME

public static final String TAG_RULES_URL_PARAMETER_NAME

See Also:

Constant Field Values

TAG_ENCODING_PARAMETER_NAME

public static final String TAG_ENCODING_PARAMETER_NAME

See Also:

Constant Field Values

BASE_TOKEN_ANNOTATION_TYPE_PARAMETER_NAME

public static final String BASE_TOKEN_ANNOTATION_TYPE_PARAMETER_NAME

See Also:

Constant Field Values

OUTPUT_ANNOTATION_TYPE_PARAMETER_NAME

public static final String OUTPUT_ANNOTATION_TYPE_PARAMETER_NAME

See Also:

Constant Field Values

BASE_SENTENCE_ANNOTATION_TYPE_PARAMETER_NAME

public static final String BASE_SENTENCE_ANNOTATION_TYPE_PARAMETER_NAME

See Also:

Constant Field Values

TAG_OUTPUT_AS_PARAMETER_NAME

public static final String TAG_OUTPUT_AS_PARAMETER_NAME

See Also:

Constant Field Values

failOnMissingInputAnnotations

protected Boolean failOnMissingInputAnnotations

logger

protected org.apache.log4j.Logger logger

tagger

protected POSTagger tagger

Constructor Detail

POSTagger

public POSTagger()

Method Detail

setFailOnMissingInputAnnotations

@RunTime
@Optional
@CreoleParameter(comment="Throw and exception when there are none of the required input annotations",
                 defaultValue="true")
public void setFailOnMissingInputAnnotations(Boolean fail)

getFailOnMissingInputAnnotations

public Boolean getFailOnMissingInputAnnotations()

init

public Resource init()
              throws ResourceInstantiationException

Description copied from class: AbstractProcessingResource

Initialise this resource, and return it.

Specified by:

init in interface Resource

Overrides:

init in class AbstractProcessingResource

Throws:

ResourceInstantiationException

execute

public void execute()
             throws ExecutionException

Description copied from class: AbstractProcessingResource

Run the resource. It doesn't make sense not to override this in subclasses so the default implementation signals an exception.

Specified by:

execute in interface Executable

Overrides:

execute in class AbstractProcessingResource

Throws:

ExecutionException

addFeatures

protected void addFeatures(Annotation annot,
                           String featureName,
                           String featureValue)
                    throws GateRuntimeException

Throws:

GateRuntimeException

setLexiconURL

public void setLexiconURL(URL newLexiconURL)

getLexiconURL

public URL getLexiconURL()

setRulesURL

public void setRulesURL(URL newRulesURL)

setEncoding

public void setEncoding(String encoding)

getRulesURL

public URL getRulesURL()

setInputASName

public void setInputASName(String newInputASName)

getInputASName

public String getInputASName()

getEncoding

public String getEncoding()

getBaseTokenAnnotationType

public String getBaseTokenAnnotationType()

getBaseSentenceAnnotationType

public String getBaseSentenceAnnotationType()

getOutputAnnotationType

public String getOutputAnnotationType()

setBaseTokenAnnotationType

public void setBaseTokenAnnotationType(String baseTokenAnnotationType)

setBaseSentenceAnnotationType

public void setBaseSentenceAnnotationType(String baseSentenceAnnotationtype)

setOutputAnnotationType

public void setOutputAnnotationType(String outputAnnotationType)

getOutputASName

public String getOutputASName()

setOutputASName

public void setOutputASName(String outputASName)