ctakes assertion - apache/ctakes GitHub Wiki
The assertion annotators provide a mechanism for examining and documenting the real-world implications for annotations in text.
For example, one might assume that a mention of "diabetes" in text implies that patient has diabetes.
However, the assertion module will consider whether a named entity or event is negated, uncertain,
used in a generic way, or in the context of a person's history.
Additionally, the subject of the statement may be someone other than the patient
(e.g., the patient's father, for "father has hx of diabetes").
Each of these attributes illustrate how the "assertion" value of a named entity might be marked.
The annotators set the value of their attribute using constants in
org.apache.ctakes.typesystem.type.constants.CONST
Collection Readers
Annotation Engines
Output Writers
Utilities
Piper Files
Reads lines from file named by AssertionConst.NEGEX_CORPUS
Source class: NegExCorpusReader
Source package: org.apache.ctakes.assertion.cr
Parent class: org.apache.uima.collection.CollectionReader_ImplBase
Products: Document Id, Identified Annotation
No available configuration parameters.
Reads document texts and annotations from XMI files specified in a provided list.
Source class: XMIReader
Source package: org.apache.ctakes.assertion.eval
Parent class: org.apache.uima.fit.component.JCasCollectionReader_ImplBase
Products: Document Id
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| files | The XMI files to be loaded | List | Yes |
Reads document texts and annotations from XMI files in a directory.
Source class: XmiCollectionReaderCtakes
Source package: org.apache.ctakes.assertion.cr
Parent class: org.apache.uima.collection.CollectionReader_ImplBase
Products: Document Id
No available configuration parameters.
Adds Negation, Uncertainty, Conditional and Subject to annotations.
Source class: AssertionAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts
Parent class: org.apache.uima.analysis_component.JCasAnnotator_ImplBase
Dependencies: Identified Annotation
No available configuration parameters.
Adds Negation, Uncertainty, Conditional and Subject to annotations.
Source class: AssertionAnalysisEngineFit
Source package: org.apache.ctakes.assertion.medfacts
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Dependencies: Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| assertionModelResource | String | Yes | org/apache/ctakes/assertion/models/ i2b2.model | |
| cueModelResource | String | Yes | org/apache/ctakes/assertion/models/ cue.model | |
| enabledFeaturesResource | String | Yes | org/apache/ctakes/assertion/models/ featureFile11b | |
| posModelResource | String | Yes | org/apache/ctakes/assertion/models/ pos.model | |
| scopeModelResource | String | Yes | org/apache/ctakes/assertion/models/ scope.model |
Determines whether or not Identified Annotations are conditional.
Source class: ConditionalCleartkAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine
Dependencies: Identified Annotation
Usables: Document Id
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Determines whether or not Identified Annotations are conditional.
Source class: ConditionalCleartkAnalysisEngineWindowed
Source package: org.apache.ctakes.assertion.medfacts.cleartk.windowed
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.windowed.WindowedAssertionCleartkAnalysisEngine
Dependencies: Identified Annotation
Usables: Document Id
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Creates a simple Concept for each Identified Annotation.
Source class: ConceptConverterAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts
Parent class: org.apache.uima.analysis_component.JCasAnnotator_ImplBase
Dependencies: Identified Annotation
No available configuration parameters.
Annotates the Generic status for Identified Annotations.
Source class: GenericAttributeAnalysisEngine
Source package: org.apache.ctakes.assertion.attributes
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Dependencies: Sentence, Identified Annotation
No available configuration parameters.
Annotates the Generic status for Identified Annotations.
Source class: GenericCleartkAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotates the Generic status for Identified Annotations.
Source class: GenericCleartkAnalysisEngineWindowed
Source package: org.apache.ctakes.assertion.medfacts.cleartk.windowed
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.windowed.WindowedAssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotate History of property.
Source class: HistoryCleartkAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotate History of property.
Source class: HistoryCleartkAnalysisEngineWindowed
Source package: org.apache.ctakes.assertion.medfacts.cleartk.windowed
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.windowed.WindowedAssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotates negation property.
Source class: PolarityCleartkAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.AssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotates negation property.
Source class: PolarityCleartkAnalysisEngineWindowed
Source package: org.apache.ctakes.assertion.medfacts.cleartk.windowed
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.windowed.WindowedAssertionCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Annotates negation property.
Source class: PolarityFedaCleartkAnalysisEngine
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.ctakes.assertion.medfacts.cleartk.PolarityCleartkAnalysisEngine
Dependencies: Sentence, Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| classifierFactoryClassName | provides the full name of the ClassifierFactory class to be used. | String | No | org.cleartk.ml.jar. JarClassifierFactory |
| dataWriterFactoryClassName | provides the full name of the DataWriterFactory class to be used. | String | No | org.cleartk.ml.jar. DefaultDataWriterFactory |
| FEATURE_CONFIG | Feature configuration to use (for experiments) | FEATURE_CONFIG | No | |
| FeatureSelectionURI | provides a URI where the feature selection data will be written | URI | No | |
| GoldViewName | view containing the manual identified annotations (especially EntityMention and EventMention annotations); needed for training | String | No | |
| isTraining | 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. | Boolean | No | |
| mapTrainFileToDomain | a map of filenames to their respective domains (i.e., directories that contain them) | String | No | |
| PortionOfDataToUse | How much data to actually use during training (e.g. for building learning curves) | double | No | |
| PrintErrors | Print errors true/false | boolean | No | false |
| ProbabilityOfKeepingADefaultExample | probability that a default example should be retained for training | double | No | |
| WhetherToDoFeatureSelection | the Chi-squared threshold at which features should be removed | Float | No |
Reads assertion cue words from file and annotates them.
Source class: AlternateCuePhraseAnnotator
Source package: org.apache.ctakes.assertion.medfacts.cleartk
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Dependencies: Base Token
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| INPUT_FILE | Directory containing cue phrase files | String | No |
Writes XMI File based upon judged attributes.
Source class: JudgeAttributeInstances
Source package: org.apache.ctakes.assertion.cc
Parent class: org.apache.uima.fit.component.JCasConsumer_ImplBase
Dependencies: Identified Annotation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| outputDirectoryName | takes a path to directory into which output files will be written. | String | Yes | |
| xmlSchemeName | specifies the UIMA XML serialization scheme that should be used. Valid values for this parameter are 'XMI' (default) and 'XCAS'. | String | Yes | XMI |
Read in gold annotations from XMI and create a view within the current CAS, and copy the gold annotations into the new view within the current CAS.
Source class: MergeGoldViewFromOneCasIntoInitialViewOfAnotherCas
Source package: org.apache.ctakes.assertion.eval
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Dependencies: Document Id
Products: Identified Annotation
No available configuration parameters.
Reads entities and their properties from file.
Source class: I2B2Challenge2010CollectionReader
Source package: org.apache.ctakes.assertion.cr
Parent class: org.apache.uima.collection.CollectionReader_ImplBase
Products: Document Id, Identified Annotation
No available configuration parameters.
Read named entity annotations from knowtator xml files into the CAS.
Source class: GoldEntityAndAttributeReader
Source package: org.apache.ctakes.assertion.cr
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Products: Identified Annotation, Generic Relation
No available configuration parameters.
Reads annotations from MiPACQ schema Knowtator XML files in a directory.
Source class: MiPACQKnowtatorXMLReader
Source package: org.apache.ctakes.assertion.cr
Parent class: org.apache.uima.fit.component.JCasAnnotator_ImplBase
Products: Identified Annotation, Generic Relation
| Parameter | Description | Class | Required | Default |
|---|---|---|---|---|
| TextDirectory | directory containing the text files (if DocumentIDs are just filenames); defaults to assuming that DocumentIDs are full file paths | File | Yes | |
| SetDefaults | whether or not to set default attribute values if no annotation is present | boolean | No |
Commands and parameters to create a default entity attributes processing sub-pipeline.
$\textcolor{gray}{\textsf{// Commands and parameters to create a default entity attributes processing sub-pipeline. }}$
$\textcolor{gray}{\textsf{// This is not a full pipeline. }}$
$\textcolor{gray}{\textsf{// Add the Dependency parser for use by assertion }}$
$\textcolor{green}{\textbf{addDescription}}$ ClearNLPDependencyParserAE
$\textcolor{gray}{\textsf{// Add the Semantic Role Labeler parser for use by assertion }}$
$\textcolor{green}{\textbf{add}}$ ClearNLPSemanticRoleLabelerAE
$\textcolor{gray}{\textsf{// Add the assertion packages for class lookups }}$
$\textcolor{orange}{\textbf{package}}$ $\textcolor{blue}{\textsf{org.apache.ctakes.assertion.medfacts}}$
$\textcolor{orange}{\textbf{package}}$ $\textcolor{blue}{\textsf{org.apache.ctakes.assertion.attributes}}$
$\textcolor{green}{\textbf{add}}$ ConceptConverterAnalysisEngine
$\textcolor{green}{\textbf{add}}$ AssertionAnalysisEngineFit
$\textcolor{green}{\textbf{add}}$ GenericAttributeAnalysisEngine
$\textcolor{green}{\textbf{add}}$ $\textcolor{blue}{\textsf{SubjectAttributeAnalysisEngine}}$
Commands and parameters to create a default entity attributes processing sub-pipeline.
$\textcolor{gray}{\textsf{// Commands and parameters to create a default entity attributes processing sub-pipeline. }}$
$\textcolor{gray}{\textsf{// This is not a full pipeline. }}$
$\textcolor{gray}{\textsf{// Add the Dependency parser for use by SubjectCleartkAnalysisEngine. }}$
$\textcolor{gray}{\textsf{// If you remove the Subject annotator you might be able to remove the dependency parser. }}$
$\textcolor{green}{\textbf{addDescription}}$ ClearNLPDependencyParserAE
$\textcolor{gray}{\textsf{// Add the Semantic Role Labeler parser for use by cleartk. }}$
$\textcolor{gray}{\textsf{// Not necessary for assertion anymore, but it is used for temporal, coref, and others so be careful removing this. }}$
$\textcolor{green}{\textbf{add}}$ ClearNLPSemanticRoleLabelerAE
$\textcolor{green}{\textbf{addDescription}}$ PolarityCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{UncertaintyCleartkAnalysisEngine}}$
$\textcolor{green}{\textbf{addDescription}}$ HistoryCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ ConditionalCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ GenericCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{SubjectCleartkAnalysisEngine}}$
Commands and parameters to create a thread-safe default entity attributes processing sub-pipeline.
$\textcolor{gray}{\textsf{// Commands and parameters to create a thread-safe default entity attributes processing sub-pipeline. }}$
$\textcolor{gray}{\textsf{// This is not a full pipeline. }}$
$\textcolor{gray}{\textsf{// Add the Dependency parser for use by cleartk }}$
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{concurrent.ThreadSafeClearNlpDepParser}}$
$\textcolor{gray}{\textsf{// Add the Semantic Role Labeler parser for use by cleartk }}$
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{concurrent.ThreadSafeClearNlpSemRoleLabeler}}$
$\textcolor{gray}{\textsf{// Add the cleartk package for cleartk class lookups }}$
$\textcolor{orange}{\textbf{package}}$ $\textcolor{blue}{\textsf{org.apache.ctakes.assertion.medfacts.cleartk}}$
$\textcolor{gray}{\textsf{// Add the cleartk attribute engines, logging for them as a block }}$
$\textcolor{green}{\textbf{add}}$ StartFinishLogger$\textcolor{purple}{\textbf{LOGGER\_NAME}}$ =$\textcolor{violet}{\textsf{CleartkAnalysisEngine}}$ $\textcolor{purple}{\textbf{LOGGER\_TASK}}$ =$\textcolor{violet}{\textsf{"Assigning Attributes"}}$
$\textcolor{green}{\textbf{addDescription}}$ PolarityCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{UncertaintyCleartkAnalysisEngine}}$
$\textcolor{green}{\textbf{addDescription}}$ HistoryCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ ConditionalCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ GenericCleartkAnalysisEngine
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{SubjectCleartkAnalysisEngine}}$
$\textcolor{green}{\textbf{add}}$ StartFinishLogger$\textcolor{purple}{\textbf{LOGGER\_NAME}}$ =$\textcolor{violet}{\textsf{CleartkAnalysisEngine}}$ $\textcolor{purple}{\textbf{LOGGER\_TASK}}$ =$\textcolor{violet}{\textsf{"Assigning Attributes"}}$
Commands and parameters to create a default entity attributes processing sub-pipeline for large files. This is not a full pipeline.
Windowed Attribute Cleartk Sub Pipe
$\textcolor{gray}{\textsf{// Commands and parameters to create a default entity attributes processing sub-pipeline for large files. This is not a full pipeline. }}$
$\textcolor{gray}{\textsf{// Add the Dependency parser for use by cleartk }}$
$\textcolor{green}{\textbf{addDescription}}$ ClearNLPDependencyParserAE
$\textcolor{gray}{\textsf{// Add the Semantic Role Labeler parser for use by cleartk }}$
$\textcolor{green}{\textbf{add}}$ ClearNLPSemanticRoleLabelerAE
$\textcolor{gray}{\textsf{// Add the cleartk package for cleartk class lookups }}$
$\textcolor{orange}{\textbf{package}}$ $\textcolor{blue}{\textsf{org.apache.ctakes.assertion.medfacts.cleartk}}$
$\textcolor{orange}{\textbf{package}}$ $\textcolor{blue}{\textsf{org.apache.ctakes.assertion.medfacts.cleartk.windowed}}$
$\textcolor{gray}{\textsf{// Add the cleartk attribute engines, logging for them as a block }}$
$\textcolor{green}{\textbf{add}}$ StartFinishLogger$\textcolor{purple}{\textbf{LOGGER\_NAME}}$ =$\textcolor{violet}{\textsf{CleartkAnalysisEngine}}$ $\textcolor{purple}{\textbf{LOGGER\_TASK}}$ =$\textcolor{violet}{\textsf{"Assigning Attributes"}}$
$\textcolor{green}{\textbf{addDescription}}$ PolarityCleartkAnalysisEngineWindowed
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{UncertaintyCleartkAnalysisEngineWindowed}}$
$\textcolor{green}{\textbf{addDescription}}$ HistoryCleartkAnalysisEngineWindowed
$\textcolor{green}{\textbf{addDescription}}$ ConditionalCleartkAnalysisEngineWindowed
$\textcolor{green}{\textbf{addDescription}}$ GenericCleartkAnalysisEngineWindowed
$\textcolor{green}{\textbf{addDescription}}$ $\textcolor{blue}{\textsf{SubjectCleartkAnalysisEngineWindowed}}$
$\textcolor{green}{\textbf{add}}$ StartFinishLogger$\textcolor{purple}{\textbf{LOGGER\_NAME}}$ =$\textcolor{violet}{\textsf{CleartkAnalysisEngine}}$ $\textcolor{purple}{\textbf{LOGGER\_TASK}}$ =$\textcolor{violet}{\textsf{"Assigning Attributes"}}$