edu.stanford.nlp.parser.metrics
Class LeafAncestorEval
java.lang.Object
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
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
optionArgDefs
public static final Map<String,Integer> optionArgDefs
LeafAncestorEval
public LeafAncestorEval(String str)
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