Bootstraps the CAS by:
Transforms document's original CDA text into plain text,
inserting section (segment) markers into text .
Transformation also inserts hyphens into words that should be hyphenated
Stores the resulting text in a new View (which has its own Sofa)
Detects sections and adds Segment (aka section) annotations
Extracts document level data and stores in CAS as Property annotations.
Selects features via Chi-squared statistics between the features extracted from its sub-extractor
and the outcome values they are paired with in classification instances.
A phrase-level conjunction
Equivalent to cTAKES: edu.mayo.bmi.uima.chunker.type.CONJP
Updated by JCasGen Tue Apr 09 12:44:03 EDT 2013
XML source: trunk/ctakes-pad-term-spotter-res/src/main/resources/org/apache/ctakes/padtermspotter/types/TypeSystem.xml
CONJP() -
Constructor for class org.apache.ctakes.typesystem.type.syntax.CONJP
"ContextAnalyzerClass" is a required, single, string parameter that
specifies the context analyzer class that determines if a "hit" is found
within a processed scope.
"ContextAnnotationClass" is a required, single, string parameter that
specifies the annotation type of the context annotations (often "tokens")
that make up the context relative to a focus annotation within a scope
that is being examined.
"ContextHitConsumerClass" is a required, single, string parameter that
specifies the context hit consumer class that will process context hits
that are found.
A coreference pair, with antecedent as arg1 and anaphor as arg2
Updated by JCasGen Tue Apr 09 12:44:02 EDT 2013
XML source: trunk/ctakes-pad-term-spotter-res/src/main/resources/org/apache/ctakes/padtermspotter/types/TypeSystem.xml
Driver for populating a Lucene Index with assertion cue phrases, so that the
tokenization of the dictionary entries matches the tokenization that will be
done to clinical text during pipeline processing.