edu.stanford.nlp.tagger.maxent
Class LambdaSolveTagger

java.lang.Object
  extended by edu.stanford.nlp.maxent.iis.LambdaSolve
      extended by edu.stanford.nlp.tagger.maxent.LambdaSolveTagger

public class LambdaSolveTagger
extends LambdaSolve

This module does the working out of lambda parameters for binary tagger features. It can use either IIS or CG.

Author:
Kristina Toutanova

Field Summary
 
Fields inherited from class edu.stanford.nlp.maxent.iis.LambdaSolve
convertValues, eps, fixedFnumXY, fnumArr, ftildeArr, lambda, lambda_converged, newtonerr, p, probConds, smooth, weightRanks, zlambda
 
Method Summary
 boolean checkCorrectness()
          Works out whether the model expectations match the empirical expectations.
 void readOldLambdas(String filename, String oldfilename)
           
 
Methods inherited from class edu.stanford.nlp.maxent.iis.LambdaSolve
divide, expectedValue, fnum, GainCompute, getDerivatives, getDerivativesExpectedValue, getDerivativesLossDomination, getDerivativesNeg, ImprovedIterative, ImprovedIterative, logLikelihood, logLikelihoodNeg, logLikelihoodScratch, lossDomination, main, pcond, print, read_lambdas, read, readL, readL, save_lambdas, save_lambdas, save, save, setBinary, setNonBinary, transformValues
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Method Detail

readOldLambdas

public void readOldLambdas(String filename,
                           String oldfilename)

checkCorrectness

public boolean checkCorrectness()
Works out whether the model expectations match the empirical expectations.

Overrides:
checkCorrectness in class LambdaSolve
Returns:
Whether the model is correct


Stanford NLP Group