public class EntityAnnotator
extends org.apache.uima.analysis_component.JCasAnnotator_ImplBase
| Modifier and Type | Field and Description |
|---|---|
protected static String |
ABBREV_PATTERN |
Pattern |
abbrevPattern |
protected float |
confidenceThresholdForConsistencyPreservation |
protected ConsistencyPreservation |
consistencyPreservation |
protected TreeSet<String> |
entityMentionTypes |
protected boolean |
expandAbbr |
protected NegativeList |
negativeList |
protected boolean |
showSegmentConf |
| Constructor and Description |
|---|
EntityAnnotator() |
| Modifier and Type | Method and Description |
|---|---|
protected Sentence |
createUnitSentence(List<Token> tokenList,
org.apache.uima.jcas.JCas JCas,
ArrayList<HashMap<String,String>> metaList,
JCoReCoverIndex<Abbreviation> abbreviationIndex,
JCoReCoverIndex<Token> tokenIndex)
Takes all info about meta data and generates the corresponding unit
sequence represented by a Sentence object.
|
protected boolean |
ignoreLabel(org.apache.uima.jcas.JCas aJCas,
int start,
int end,
JCoReCoverIndex<Abbreviation> abbreviationIndex)
tests whether annotation should be ignored as this label is on a not
introduced abbreviation
|
void |
initialize(org.apache.uima.UimaContext aContext)
Initialisiation of UIMA-JNET.
|
void |
process(org.apache.uima.jcas.JCas aJCas)
process current CAS.
|
protected Sentence |
removeDuplicatedTokens(Sentence unitSentence)
removes duplicate tokens in a unit sentence (i.e., tokens having the same
offset position).
|
void |
writeToCAS(Sentence unitSentence,
org.apache.uima.jcas.JCas aJCas,
JCoReCoverIndex<Abbreviation> abbreviationIndex)
creates the respective uima annotations from JNET's predictions.
|
getRequiredCasInterface, processgetCasInstancesRequired, hasNext, nextprotected static final String ABBREV_PATTERN
public Pattern abbrevPattern
protected boolean expandAbbr
protected ConsistencyPreservation consistencyPreservation
protected float confidenceThresholdForConsistencyPreservation
protected boolean showSegmentConf
protected NegativeList negativeList
public void initialize(org.apache.uima.UimaContext aContext)
throws org.apache.uima.resource.ResourceInitializationException
initialize in interface org.apache.uima.analysis_component.AnalysisComponentinitialize in class org.apache.uima.analysis_component.AnalysisComponent_ImplBaseorg.apache.uima.resource.ResourceInitializationExceptionpublic void process(org.apache.uima.jcas.JCas aJCas)
throws org.apache.uima.analysis_engine.AnalysisEngineProcessException
process in class org.apache.uima.analysis_component.JCasAnnotator_ImplBaseorg.apache.uima.analysis_engine.AnalysisEngineProcessExceptionprotected Sentence removeDuplicatedTokens(Sentence unitSentence)
protected Sentence createUnitSentence(List<Token> tokenList, org.apache.uima.jcas.JCas JCas, ArrayList<HashMap<String,String>> metaList, JCoReCoverIndex<Abbreviation> abbreviationIndex, JCoReCoverIndex<Token> tokenIndex)
tokenList - a list of Token objects of the current sentenceJCas - the CAS we are working onmetaList - a Arraylist of meta-info HashMaps which specify the meta
information of the respective tokenabbreviationIndex - tokenIndex - public void writeToCAS(Sentence unitSentence, org.apache.uima.jcas.JCas aJCas, JCoReCoverIndex<Abbreviation> abbreviationIndex)
unitSentence - the current Sentence objectaJCas - the cas to write the annotation toabbreviationIndex - protected boolean ignoreLabel(org.apache.uima.jcas.JCas aJCas,
int start,
int end,
JCoReCoverIndex<Abbreviation> abbreviationIndex)
aJCas - start - end - abbreviationIndex - coveredText - Copyright © 2019 JULIE Lab Jena, Germany. All rights reserved.