uk.ac.man.entitytagger.matching
Class Postprocessor

java.lang.Object
  extended by uk.ac.man.entitytagger.matching.Postprocessor
Direct Known Subclasses:
CellLinePostprocessor

public class Postprocessor
extends java.lang.Object


Field Summary
private  java.util.Map<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> acronymProbabilities
           
protected  java.util.Map<java.lang.String,java.lang.String> comments
           
private  java.util.Map<java.lang.String,java.lang.Integer> entityFrequencies
           
private  java.util.Map<java.lang.String,java.util.List<java.util.regex.Pattern>> stopTerms
           
 
Constructor Summary
Postprocessor(java.io.File[] stopTermFile, java.io.File[] acronymProbFile, java.io.File[] entityFrequencyFile, java.util.Map<java.lang.String,java.lang.String> comments, java.util.logging.Logger logger)
           
Postprocessor(java.io.InputStream[] stopTermStreams, java.io.InputStream[] acronymProbStreams, java.io.InputStream[] entityFrequencyStreams, java.util.Map<java.lang.String,java.lang.String> comments, java.util.logging.Logger logger)
           
 
Method Summary
 void comment(java.util.List<Mention> matches, java.util.Map<java.lang.String,java.lang.String> comments2)
           
private  java.util.List<Mention> filterByStopTerms(java.util.List<Mention> matches)
           
private  java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> loadAcronymProbabilities(java.io.File[] acronymProbFiles)
           
private  java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> loadAcronymProbabilities(java.io.InputStream[] acronymProbStreams)
           
private  java.util.Map<java.lang.String,java.lang.Integer> loadEntityFrequencies(java.io.File[] entityFreqFiles)
           
private  java.util.Map<java.lang.String,java.lang.Integer> loadEntityFrequencies(java.io.InputStream[] entityFrequencyStreams)
           
private  java.util.HashMap<java.lang.String,java.util.List<java.util.regex.Pattern>> loadStopTerms(java.io.File[] entityFreqFiles)
           
private  java.util.HashMap<java.lang.String,java.util.List<java.util.regex.Pattern>> loadStopTerms(java.io.InputStream[] stopTermStreams)
           
 java.util.List<Mention> postProcess(java.util.List<Mention> matches, java.lang.String text)
           
private  void removeLineNumbers(java.util.List<Mention> matches)
           
 void setProbs(java.util.List<Mention> matches)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

stopTerms

private java.util.Map<java.lang.String,java.util.List<java.util.regex.Pattern>> stopTerms

acronymProbabilities

private java.util.Map<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> acronymProbabilities

entityFrequencies

private java.util.Map<java.lang.String,java.lang.Integer> entityFrequencies

comments

protected java.util.Map<java.lang.String,java.lang.String> comments
Constructor Detail

Postprocessor

public Postprocessor(java.io.File[] stopTermFile,
                     java.io.File[] acronymProbFile,
                     java.io.File[] entityFrequencyFile,
                     java.util.Map<java.lang.String,java.lang.String> comments,
                     java.util.logging.Logger logger)

Postprocessor

public Postprocessor(java.io.InputStream[] stopTermStreams,
                     java.io.InputStream[] acronymProbStreams,
                     java.io.InputStream[] entityFrequencyStreams,
                     java.util.Map<java.lang.String,java.lang.String> comments,
                     java.util.logging.Logger logger)
Method Detail

loadEntityFrequencies

private java.util.Map<java.lang.String,java.lang.Integer> loadEntityFrequencies(java.io.File[] entityFreqFiles)

loadEntityFrequencies

private java.util.Map<java.lang.String,java.lang.Integer> loadEntityFrequencies(java.io.InputStream[] entityFrequencyStreams)

loadAcronymProbabilities

private java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> loadAcronymProbabilities(java.io.File[] acronymProbFiles)

loadAcronymProbabilities

private java.util.HashMap<java.lang.String,java.util.HashMap<java.lang.String,java.lang.Double>> loadAcronymProbabilities(java.io.InputStream[] acronymProbStreams)

loadStopTerms

private java.util.HashMap<java.lang.String,java.util.List<java.util.regex.Pattern>> loadStopTerms(java.io.File[] entityFreqFiles)

loadStopTerms

private java.util.HashMap<java.lang.String,java.util.List<java.util.regex.Pattern>> loadStopTerms(java.io.InputStream[] stopTermStreams)

postProcess

public java.util.List<Mention> postProcess(java.util.List<Mention> matches,
                                           java.lang.String text)

removeLineNumbers

private void removeLineNumbers(java.util.List<Mention> matches)

comment

public void comment(java.util.List<Mention> matches,
                    java.util.Map<java.lang.String,java.lang.String> comments2)

setProbs

public void setProbs(java.util.List<Mention> matches)

filterByStopTerms

private java.util.List<Mention> filterByStopTerms(java.util.List<Mention> matches)