edu.stanford.nlp.parser.metrics
Class LeafAncestorEval

java.lang.Object
  extended by edu.stanford.nlp.parser.metrics.LeafAncestorEval

public class LeafAncestorEval
extends Object

Implementation of the Leaf Ancestor metric first described by Sampson and Babarczy (2003) and later analyzed more completely by Clegg and Shepherd (2005).

This implementation assumes that the guess/gold input files are of equal length, and have one tree per line.

TODO (spenceg): This implementation doesn't insert the "boundary symbols" as described by both Sampson and Clegg. Need to add those.

Author:
Spence Green

Field Summary
static Map<String,Integer> optionArgDefs
           
 
Constructor Summary
LeafAncestorEval(String str)
           
 
Method Summary
 void display(boolean verbose, PrintWriter pw)
           
 void evaluate(Tree guess, Tree gold, PrintWriter pw)
           
static void main(String[] args)
          Execute with no arguments for usage.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

optionArgDefs

public static final Map<String,Integer> optionArgDefs
Constructor Detail

LeafAncestorEval

public LeafAncestorEval(String str)
Method Detail

evaluate

public void evaluate(Tree guess,
                     Tree gold,
                     PrintWriter pw)

display

public void display(boolean verbose,
                    PrintWriter pw)

main

public static void main(String[] args)
Execute with no arguments for usage.



Stanford NLP Group