ctakes-relation-extractor/desc/analysis_engine/RelationExtractorAggregate.xml (448 lines of code) (raw):

<?xml version="1.0" encoding="UTF-8"?> <!-- Licensed to the Apache Software Foundation (ASF) under one or more contributor license agreements. See the NOTICE file distributed with this work for additional information regarding copyright ownership. The ASF licenses this file to you under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License. --> <analysisEngineDescription xmlns="http://uima.apache.org/resourceSpecifier"> <frameworkImplementation>org.apache.uima.java</frameworkImplementation> <primitive>false</primitive> <delegateAnalysisEngineSpecifiers> <delegateAnalysisEngine key="LocationOfRelationExtractorAnnotator"> <analysisEngineDescription> <frameworkImplementation>org.apache.uima.java</frameworkImplementation> <primitive>true</primitive> <annotatorImplementationName>org.apache.ctakes.relationextractor.ae.LocationOfRelationExtractorAnnotator</annotatorImplementationName> <analysisEngineMetaData> <name>LocationOfRelationExtractorAnnotator</name> <description>Descriptor automatically generated by uimaFIT</description> <version>unknown</version> <vendor>org.apache.ctakes.relationextractor.ae</vendor> <configurationParameters> <configurationParameter> <name>ProbabilityOfKeepingANegativeExample</name> <description>probability that a negative example should be retained for training</description> <type>Float</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>classifierFactoryClassName</name> <description>provides the full name of the ClassifierFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>dataWriterFactoryClassName</name> <description>provides the full name of the DataWriterFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>isTraining</name> <description>determines whether this annotator is writing training data or using a classifier to annotate. Normally inferred automatically based on whether or not a DataWriterFactory class has been set.</description> <type>Boolean</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>classifierJarPath</name> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> </configurationParameters> <configurationParameterSettings> <nameValuePair> <name>classifierFactoryClassName</name> <value> <string>org.cleartk.ml.jar.JarClassifierFactory</string> </value> </nameValuePair> <nameValuePair> <name>dataWriterFactoryClassName</name> <value> <string>org.cleartk.ml.jar.DefaultDataWriterFactory</string> </value> </nameValuePair> <nameValuePair> <name>ProbabilityOfKeepingANegativeExample</name> <value> <float>0.5</float> </value> </nameValuePair> <nameValuePair> <name>classifierJarPath</name> <value> <string>/org/apache/ctakes/relation/extractor/models/location_of/model.jar</string> </value> </nameValuePair> </configurationParameterSettings> <typeSystemDescription> <imports> <import name="org.apache.ctakes.typesystem.types.TypeSystem"/> </imports> </typeSystemDescription> <typePriorities/> <fsIndexCollection/> <capabilities/> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> </analysisEngineDescription> </delegateAnalysisEngine> <delegateAnalysisEngine key="RelationExtractorPreprocessor"> <analysisEngineDescription> <frameworkImplementation>org.apache.uima.java</frameworkImplementation> <primitive>false</primitive> <delegateAnalysisEngineSpecifiers> <delegateAnalysisEngine key="TokenizerAnnotator"> <import location="../../../ctakes-core/desc/analysis_engine/TokenizerAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="ClearNLPAE"> <import location="../../../ctakes-dependency-parser/desc/analysis_engine/ClearNLPDependencyParserAE.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="ContextDependentTokenizerAnnotator"> <import location="../../../ctakes-context-tokenizer/desc/analysis_engine/ContextDependentTokenizerAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="ConstituencyParser"> <import location="../../../ctakes-constituency-parser/desc/ConstituencyParserAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="StatusAnnotator"> <import location="../../../ctakes-ne-contexts/desc/StatusAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="NegationAnnotator"> <import location="../../../ctakes-ne-contexts/desc/NegationAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="SentenceDetectorAnnotator"> <import location="../../../ctakes-core/desc/analysis_engine/SentenceDetectorAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="AdjustNounPhraseToIncludeFollowingNP"> <import location="../../../ctakes-chunker/desc/AdjustNounPhraseToIncludeFollowingNP.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="AdjustNounPhraseToIncludeFollowingPPNP"> <import location="../../../ctakes-chunker/desc/AdjustNounPhraseToIncludeFollowingPPNP.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="SimpleSegmentAnnotator"> <import location="../../../ctakes-clinical-pipeline/desc/analysis_engine/SimpleSegmentAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="POSTagger"> <import location="../../../ctakes-pos-tagger/desc/POSTagger.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="Chunker"> <import location="../../../ctakes-chunker/desc/Chunker.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="DictionaryLookupAnnotatorDB"> <import location="../../../ctakes-dictionary-lookup-fast/desc/analysis_engine/UmlsLookupAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="LookupWindowAnnotator"> <import location="../../../ctakes-clinical-pipeline/desc/analysis_engine/LookupWindowAnnotator.xml"/> </delegateAnalysisEngine> <delegateAnalysisEngine key="LvgAnnotator"> <import location="../../../ctakes-lvg/desc/analysis_engine/LvgAnnotator.xml"/> </delegateAnalysisEngine> </delegateAnalysisEngineSpecifiers> <analysisEngineMetaData> <name>RelationExtractorPreprocessor</name> <description>Same as AggregateRelationExtractorUMLSProcessor, without the RelationExtractorAnnotator.</description> <version/> <vendor/> <configurationParameters searchStrategy="language_fallback"> <configurationParameter> <name>SegmentID</name> <description/> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> <overrides> <parameter>SimpleSegmentAnnotator/SegmentID</parameter> </overrides> </configurationParameter> <configurationParameter> <name>ChunkCreatorClass</name> <type>String</type> <multiValued>false</multiValued> <mandatory>true</mandatory> <overrides> <parameter>Chunker/ChunkCreatorClass</parameter> </overrides> </configurationParameter> </configurationParameters> <configurationParameterSettings> <nameValuePair> <name>ChunkCreatorClass</name> <value> <string>org.apache.ctakes.chunker.ae.PhraseTypeChunkCreator</string> </value> </nameValuePair> </configurationParameterSettings> <flowConstraints> <fixedFlow> <node>SimpleSegmentAnnotator</node> <node>SentenceDetectorAnnotator</node> <node>TokenizerAnnotator</node> <node>LvgAnnotator</node> <node>ContextDependentTokenizerAnnotator</node> <node>POSTagger</node> <node>ConstituencyParser</node> <node>ClearNLPAE</node> <node>Chunker</node> <node>AdjustNounPhraseToIncludeFollowingNP</node> <node>AdjustNounPhraseToIncludeFollowingPPNP</node> <node>LookupWindowAnnotator</node> <node>DictionaryLookupAnnotatorDB</node> <node>StatusAnnotator</node> <node>NegationAnnotator</node> </fixedFlow> </flowConstraints> <typePriorities> <name>Ordering</name> <description>For subiterator</description> <version>1.0</version> <priorityList> <type>org.apache.ctakes.typesystem.type.textspan.Segment</type> <type>org.apache.ctakes.typesystem.type.textspan.Sentence</type> <type>org.apache.ctakes.typesystem.type.syntax.BaseToken</type> </priorityList> <priorityList> <type>org.apache.ctakes.typesystem.type.textspan.Sentence</type> <type>org.apache.ctakes.typesystem.type.textsem.IdentifiedAnnotation</type> </priorityList> </typePriorities> <fsIndexCollection/> <capabilities> <capability> <inputs/> <outputs> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.NewlineToken</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.IdentifiedAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.WordToken</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.VP</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.refsem.UmlsConcept</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.UCP</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.TimeAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.SymbolToken</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textspan.Sentence</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.SBAR</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.RomanNumeralAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.RangeAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.PunctuationToken</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.PersonTitleAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.PRT</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.PP</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.NumToken</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.MeasurementAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.Lemma</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.LST</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.INTJ</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.FractionAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.structured.DocumentID</type> <type allAnnotatorFeatures="true">uima.tcas.DocumentAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.DateAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.CopySrcAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.CopyDestAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.textsem.ContextAnnotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.Chunk</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.CONJP</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.BaseToken</type> <type allAnnotatorFeatures="true">uima.cas.AnnotationBase</type> <type allAnnotatorFeatures="true">uima.tcas.Annotation</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.ADVP</type> <type allAnnotatorFeatures="true">org.apache.ctakes.typesystem.type.syntax.ADJP</type> </outputs> <languagesSupported/> </capability> </capabilities> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> <resourceManagerConfiguration/> </analysisEngineDescription> </delegateAnalysisEngine> <delegateAnalysisEngine key="DegreeOfRelationExtractorAnnotator"> <analysisEngineDescription> <frameworkImplementation>org.apache.uima.java</frameworkImplementation> <primitive>true</primitive> <annotatorImplementationName>org.apache.ctakes.relationextractor.ae.DegreeOfRelationExtractorAnnotator</annotatorImplementationName> <analysisEngineMetaData> <name>DegreeOfRelationExtractorAnnotator</name> <description>Descriptor automatically generated by uimaFIT</description> <version>unknown</version> <vendor>org.apache.ctakes.relationextractor.ae</vendor> <configurationParameters> <configurationParameter> <name>ProbabilityOfKeepingANegativeExample</name> <description>probability that a negative example should be retained for training</description> <type>Float</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>classifierFactoryClassName</name> <description>provides the full name of the ClassifierFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>dataWriterFactoryClassName</name> <description>provides the full name of the DataWriterFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>isTraining</name> <description>determines whether this annotator is writing training data or using a classifier to annotate. Normally inferred automatically based on whether or not a DataWriterFactory class has been set.</description> <type>Boolean</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>classifierJarPath</name> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> </configurationParameters> <configurationParameterSettings> <nameValuePair> <name>classifierFactoryClassName</name> <value> <string>org.cleartk.ml.jar.JarClassifierFactory</string> </value> </nameValuePair> <nameValuePair> <name>dataWriterFactoryClassName</name> <value> <string>org.cleartk.ml.jar.DefaultDataWriterFactory</string> </value> </nameValuePair> <nameValuePair> <name>ProbabilityOfKeepingANegativeExample</name> <value> <float>0.5</float> </value> </nameValuePair> <nameValuePair> <name>classifierJarPath</name> <value> <string>/org/apache/ctakes/relation/extractor/models/degree_of/model.jar</string> </value> </nameValuePair> </configurationParameterSettings> <typeSystemDescription> <imports> <import name="org.apache.ctakes.typesystem.types.TypeSystem"/> </imports> </typeSystemDescription> <typePriorities/> <fsIndexCollection/> <capabilities/> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> </analysisEngineDescription> </delegateAnalysisEngine> <delegateAnalysisEngine key="ModifierExtractorAnnotator"> <analysisEngineDescription> <frameworkImplementation>org.apache.uima.java</frameworkImplementation> <primitive>true</primitive> <annotatorImplementationName>org.apache.ctakes.relationextractor.ae.ModifierExtractorAnnotator</annotatorImplementationName> <analysisEngineMetaData> <name>ModifierExtractorAnnotator</name> <description>Descriptor automatically generated by uimaFIT</description> <version>unknown</version> <vendor>org.apache.ctakes.relationextractor.ae</vendor> <configurationParameters> <configurationParameter> <name>classifierFactoryClassName</name> <description>provides the full name of the ClassifierFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>dataWriterFactoryClassName</name> <description>provides the full name of the DataWriterFactory class to be used.</description> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>isTraining</name> <description>determines whether this annotator is writing training data or using a classifier to annotate. Normally inferred automatically based on whether or not a DataWriterFactory class has been set.</description> <type>Boolean</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> <configurationParameter> <name>classifierJarPath</name> <type>String</type> <multiValued>false</multiValued> <mandatory>false</mandatory> </configurationParameter> </configurationParameters> <configurationParameterSettings> <nameValuePair> <name>classifierFactoryClassName</name> <value> <string>org.cleartk.ml.jar.JarClassifierFactory</string> </value> </nameValuePair> <nameValuePair> <name>dataWriterFactoryClassName</name> <value> <string>org.cleartk.ml.jar.DefaultDataWriterFactory</string> </value> </nameValuePair> <nameValuePair> <name>classifierJarPath</name> <value> <string>/org/apache/ctakes/relation/extractor/models/modifier_extractor/model.jar</string> </value> </nameValuePair> </configurationParameterSettings> <typeSystemDescription> <imports> <import name="org.apache.ctakes.typesystem.types.TypeSystem"/> </imports> </typeSystemDescription> <typePriorities/> <fsIndexCollection/> <capabilities/> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> </analysisEngineDescription> </delegateAnalysisEngine> </delegateAnalysisEngineSpecifiers> <analysisEngineMetaData> <name>RelationExtractorAggregate</name> <configurationParameters/> <configurationParameterSettings/> <flowConstraints> <fixedFlow> <node>RelationExtractorPreprocessor</node> <node>ModifierExtractorAnnotator</node> <node>DegreeOfRelationExtractorAnnotator</node> <node>LocationOfRelationExtractorAnnotator</node> </fixedFlow> </flowConstraints> <capabilities/> <operationalProperties> <modifiesCas>true</modifiesCas> <multipleDeploymentAllowed>true</multipleDeploymentAllowed> <outputsNewCASes>false</outputsNewCASes> </operationalProperties> </analysisEngineMetaData> </analysisEngineDescription>