Java StringLabelFactory类代码示例

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
public static void main(String[] args) throws IOException {
  TreeJPanel tjp = new TreeJPanel();
  // String ptbTreeString1 = "(ROOT (S (NP (DT This)) (VP (VBZ is) (NP (DT a) (NN test))) (. .)))";
  String ptbTreeString = "(ROOT (S (NP (NNP Interactive_Tregex)) (VP (VBZ works)) (PP (IN for) (PRP me)) (. !))))";
  if (args.length > 0) {
    ptbTreeString = args[0];
  }
  Tree tree = (new PennTreeReader(new StringReader(ptbTreeString), new LabeledScoredTreeFactory(new StringLabelFactory()))).readTree();
  tjp.setTree(tree);
  tjp.setBackground(Color.white);
  JFrame frame = new JFrame();
  frame.getContentPane().add(tjp, BorderLayout.CENTER);
  frame.addWindowListener(new WindowAdapter() {
    @Override
    public void windowClosing(WindowEvent e) {
      System.exit(0);
    }
  });
  frame.pack();
  frame.setVisible(true);
  frame.setVisible(true);
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * This method just tests the functionality of the included transformers.
 */
public static void main(String[] args) {
  //TreeFactory tf = new LabeledScoredTreeFactory();
  Tree stringyTree = null;
  try {
    stringyTree = (new PennTreeReader(new StringReader("(S (VP (VBZ Try) (NP (DT this))) (. .))"), new LabeledScoredTreeFactory(new StringLabelFactory()))).readTree();
  } catch (IOException e) {
  }
  System.out.println(stringyTree);
  Function<Tree, Tree> a = getLabeledTreeToCategoryWordTagTreeFunction();
  Tree adaptyTree = a.apply(stringyTree);
  System.out.println(adaptyTree);
  adaptyTree.percolateHeads(new CollinsHeadFinder());
  System.out.println(adaptyTree);

  Function<Tree, Tree> b = getLabeledTreeToStringLabeledTreeFunction();
  Tree stringLabelTree = b.apply(adaptyTree);
  System.out.println(stringLabelTree);

}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * This method just tests the functionality of the included transformers.
 */
public static void main(String[] args) {
  //TreeFactory tf = new LabeledScoredTreeFactory();
  Tree stringyTree = null;
  try {
    stringyTree = (new PennTreeReader(new StringReader("(S (VP (VBZ Try) (NP (DT this))) (. .))"), new LabeledScoredTreeFactory(new StringLabelFactory()))).readTree();
  } catch (IOException e) {
    // do nothing
  }
  System.out.println(stringyTree);
  Function<Tree, Tree> a = getLabeledTreeToCategoryWordTagTreeFunction();
  Tree adaptyTree = a.apply(stringyTree);
  System.out.println(adaptyTree);
  adaptyTree.percolateHeads(new CollinsHeadFinder());
  System.out.println(adaptyTree);

  Function<Tree, Tree> b = getLabeledTreeToStringLabeledTreeFunction();
  Tree stringLabelTree = b.apply(adaptyTree);
  System.out.println(stringLabelTree);

}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * Calculate sister annotation statistics suitable for doing
 * selective sister splitting in the PCFGParser inside the
 * FactoredParser.
 *
 * @param args One argument: path to the Treebank
 */
public static void main(String[] args) {

  ClassicCounter<String> c = new ClassicCounter<String>();
  c.setCount("A", 0);
  c.setCount("B", 1);

  double d = Counters.klDivergence(c, c);
  System.out.println("KL Divergence: " + d);


  String encoding = "UTF-8";
  if (args.length > 1) {
    encoding = args[1];
  }
  if (args.length < 1) {
    System.out.println("Usage: ParentAnnotationStats treebankPath");
  } else {
    SisterAnnotationStats pas = new SisterAnnotationStats();
    Treebank treebank = new DiskTreebank(new TreeReaderFactory() {
      public TreeReader newTreeReader(Reader in) {
        return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), new BobChrisTreeNormalizer());
      }
    }, encoding);
    treebank.loadPath(args[0]);
    treebank.apply(pas);
    pas.printStats();
  }
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * Calculate parent annotation statistics suitable for doing
 * selective parent splitting in the PCFGParser inside
 * FactoredParser.  <p>
 * Usage: java edu.stanford.nlp.parser.lexparser.ParentAnnotationStats
 * [-tags] treebankPath
 *
 * @param args One argument: path to the Treebank
 */
public static void main(String[] args) {
  if (args.length < 1) {
    System.out.println("Usage: java edu.stanford.nlp.parser.lexparser.ParentAnnotationStats [-tags] treebankPath");
  } else {
    int i = 0;
    boolean useCutOff = false;
    double cutOff = 0.0;
    while (args[i].startsWith("-")) {
      if (args[i].equals("-tags")) {
        doTags = true;
        i++;
      } else if (args[i].equals("-cutOff") && i + 1 < args.length) {
        useCutOff = true;
        cutOff = Double.parseDouble(args[i + 1]);
        i += 2;
      } else {
        System.err.println("Unknown option: " + args[i]);
        i++;
      }
    }

    Treebank treebank = new DiskTreebank(new TreeReaderFactory() {
      public TreeReader newTreeReader(Reader in) {
        return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), new BobChrisTreeNormalizer());
      }
    });
    treebank.loadPath(args[i]);

    if (useCutOff) {
      Set<String> splitters = getSplitCategories(treebank, doTags, 0, cutOff, cutOff, null);
      System.out.println(splitters);
    } else {
      ParentAnnotationStats pas = new ParentAnnotationStats();
      treebank.apply(pas);
      pas.printStats();
    }
  }
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
public TreeReader newTreeReader(Reader in) {
  final TreeNormalizer tn1 = new GrammaticalFunctionTreeNormalizer(tlp, nodeCleanup);
  final TueBaDZPennTreeNormalizer tn2 = new TueBaDZPennTreeNormalizer(tlp, nodeCleanup);
  final TreeNormalizer norm = new OrderedCombinationTreeNormalizer(Arrays.asList(tn1, tn2));

  return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), norm);
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * Create a new <code>TreeReader</code> using the provided
 * <code>Reader</code>.
 *
 * @param in The <code>Reader</code> to build on
 * @return The new TreeReader
 */
public TreeReader newTreeReader(Reader in) {
  if (discardFrags) {
    return new FragDiscardingPennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), tn, new CHTBTokenizer(in));
  } else {
    return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), tn, new CHTBTokenizer(in));
  }
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
public TreeReader newTreeReader(Reader in) {
  final NegraPennTreeNormalizer tn = new NegraPennTreeNormalizer(tlp, nodeCleanup);
  if (treeNormalizerInsertNPinPP) {
    tn.setInsertNPinPP(true);
  }

  return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), tn, new NegraPennTokenizer(in));
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * Calculate parent annotation statistics suitable for doing
 * selective parent splitting in the PCFGParser inside
 * FactoredParser.  <p>
 * Usage: java edu.stanford.nlp.parser.lexparser.ParentAnnotationStats
 * [-tags] treebankPath
 *
 * @param args One argument: path to the Treebank
 */
public static void main(String[] args) {
  boolean doTags = false;
  if (args.length < 1) {
    System.out.println("Usage: java edu.stanford.nlp.parser.lexparser.ParentAnnotationStats [-tags] treebankPath");
  } else {
    int i = 0;
    boolean useCutOff = false;
    double cutOff = 0.0;
    while (args[i].startsWith("-")) {
      if (args[i].equals("-tags")) {
        doTags = true;
        i++;
      } else if (args[i].equals("-cutOff") && i + 1 < args.length) {
        useCutOff = true;
        cutOff = Double.parseDouble(args[i + 1]);
        i += 2;
      } else {
        System.err.println("Unknown option: " + args[i]);
        i++;
      }
    }

    Treebank treebank = new DiskTreebank(new TreeReaderFactory() {
      public TreeReader newTreeReader(Reader in) {
        return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()), new BobChrisTreeNormalizer());
      }
    });
    treebank.loadPath(args[i]);

    if (useCutOff) {
      Set<String> splitters = getSplitCategories(treebank, doTags, 0, cutOff, cutOff, null);
      System.out.println(splitters);
    } else {
      ParentAnnotationStats pas = new ParentAnnotationStats(null, doTags);
      treebank.apply(pas);
      pas.printStats();
    }
  }
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
public Debinarizer(boolean forceCNF) {
  this(forceCNF, new StringLabelFactory());
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/** The tree t is normally expected to be a Penn-Treebank-style tree
 *  in which the top node is an extra node that rewrites unarily.
 *  If this isn't the case, an extra node is added and the user is
 *  warned.
 */

public Tree transformTree(Tree t) {
  if (Train.printTreeTransformations > 0) {
    Train.printTrainTree(null, "ORIGINAL TREE:", t);
  }
  Tree trTree = annotator.transformTree(t);
  if (Train.selectivePostSplit) {
    trTree = postSplitter.transformTree(trTree);
  }
  if (Train.printTreeTransformations > 0) {
    Train.printTrainTree(Train.printAnnotatedPW, "ANNOTATED TREE:", trTree);
  }
  if (Train.printAnnotatedRuleCounts) {
    Tree tr2 = trTree.deeperCopy(new LabeledScoredTreeFactory(), new StringLabelFactory());
    Set<Tree> localTrees = tr2.localTrees();
    for (Tree tr : localTrees) {
      annotatedRuleCounts.incrementCount(tr);
    }
  }
  if (Train.printAnnotatedStateCounts) {
    for (Tree subt : trTree) {
      if ( ! subt.isLeaf()) {
        annotatedStateCounts.incrementCount(subt.label().value());
      }
    }
  }

  // if we add the ROOT first, then we don't know how to percolate the heads at the top
  addRoot(trTree); // this creates a few non-binarized rules at the top

  Tree binarizedTree = binarizer.transformTree(trTree);
  if (Train.printTreeTransformations > 0) {
    Train.printTrainTree(Train.printBinarizedPW, "BINARIZED TREE:", binarizedTree);
    Train.printTreeTransformations--;
  }
  if (forceCNF) {
    binarizedTree = new CNFTransformers.ToCNFTransformer().transformTree(binarizedTree);
    //        System.out.println("BinarizedCNF:\n");
    //        binarizedTree.pennPrint();
  }
  return binarizedTree;
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
public TreeReader newTreeReader(Reader in) {
  return new PennTreeReader(new BufferedReader(in), new LabeledScoredTreeFactory(new StringLabelFactory()), tn);
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/** The tree t is normally expected to be a Penn-Treebank-style tree
 *  in which the top node is an extra node that rewrites unarily.
 *  If this isn't the case, an extra node is added and the user is
 *  warned.
 */

public Tree transformTree(Tree t) {
  if (trainOptions.printTreeTransformations > 0) {
    trainOptions.printTrainTree(null, "ORIGINAL TREE:", t);
  }
  Tree trTree = annotator.transformTree(t);
  if (trainOptions.selectivePostSplit) {
    trTree = postSplitter.transformTree(trTree);
  }
  if (trainOptions.printTreeTransformations > 0) {
    trainOptions.printTrainTree(trainOptions.printAnnotatedPW, "ANNOTATED TREE:", trTree);
  }
  if (trainOptions.printAnnotatedRuleCounts) {
    Tree tr2 = trTree.deepCopy(new LabeledScoredTreeFactory(), new StringLabelFactory());
    Set<Tree> localTrees = tr2.localTrees();
    for (Tree tr : localTrees) {
      annotatedRuleCounts.incrementCount(tr);
    }
  }
  if (trainOptions.printAnnotatedStateCounts) {
    for (Tree subt : trTree) {
      if ( ! subt.isLeaf()) {
        annotatedStateCounts.incrementCount(subt.label().value());
      }
    }
  }

  // if we add the ROOT first, then we don't know how to percolate the heads at the top
  addRoot(trTree); // this creates a few non-binarized rules at the top

  Tree binarizedTree = binarizer.transformTree(trTree);
  if (trainOptions.printTreeTransformations > 0) {
    trainOptions.printTrainTree(trainOptions.printBinarizedPW, "BINARIZED TREE:", binarizedTree);
    trainOptions.printTreeTransformations--;
  }
  if (forceCNF) {
    binarizedTree = new CNFTransformers.ToCNFTransformer().transformTree(binarizedTree);
    //        System.out.println("BinarizedCNF:\n");
    //        binarizedTree.pennPrint();
  }
  return binarizedTree;
}
 

import edu.stanford.nlp.ling.StringLabelFactory; //导入依赖的package包/类
/**
 * An implementation of the <code>TreeReaderFactory</code> interface.
 * It creates a simple <code>TreeReader</code> which literally
 * reproduces trees in the treebank as <code>LabeledScoredTree</code>
 * objects, with <code>StringLabel</code> labels.
 */
public TreeReader newTreeReader(Reader in) {
  return new PennTreeReader(in, new LabeledScoredTreeFactory(new StringLabelFactory()));
}