Examples of edu.stanford.nlp.parser.metrics.BestOfTopKEval

edu.stanford.nlp.parser.metrics.BestOfTopKEval
Applies an AbstractEval to a list of trees to pick the best tree using F1 measure. Then uses a second AbstractEval to tally statistics for the best tree chosen. This is useful for experiments to see how much the parser could improve if you were able to correctly order the top N trees.
The comparisonEval will not have any useful statistics, as it will tested against the top N trees for each parsing. The countingEval is the useful AbstractEval, as it is tallied only once per parse.
One example of this is the pcfgTopK eval, which looks for the best LP/LR of constituents in the top K trees. @author John Bauer

    }
    // this one is for the various k Good/Best options.  Just for individual results
    kGoodLB = new Evalb("kGood LP/LR", false);


    if (Boolean.parseBoolean(op.testOptions.evals.getProperty("pcfgTopK"))) {
      topKEvals.add(new BestOfTopKEval(new Evalb("pcfg top k comparisons", false), new Evalb("pcfg top k LP/LR", runningAverages)));
    }


    if (topKEvals.size() > 0) {
      kbestPCFG = op.testOptions.evalPCFGkBest;
    }

View Full Code Here

TOP

Related Classes of edu.stanford.nlp.parser.metrics.BestOfTopKEval

edu.stanford.nlp.parser.lexparser.EvaluateTreebank

edu.stanford.nlp.trees.Tree

java.io.PrintWriter

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.