edu.stanford.nlp.parser.lexparser.Debinarizer Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of stanford-corenlp Show documentation

Stanford CoreNLP provides a set of natural language analysis tools which can take raw English language text input and give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and word dependencies, and indicate which noun phrases refer to the same entities. It provides the foundational building blocks for higher level text understanding applications.

There is a newer version: 4.5.7

Show newest version

package edu.stanford.nlp.parser.lexparser;

import java.util.*;

import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.ling.LabelFactory;
import edu.stanford.nlp.trees.LabeledScoredTreeFactory;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreeFactory;
import edu.stanford.nlp.trees.TreeTransformer;

/** Debinarizes a binary tree from the parser.
 *  Node values with a '@' in them anywhere are assumed to be inserted
 *  nodes for the purpose of binarization, and are removed.
 *  The code also removes the last child of the root node, assuming
 *  that it is an inserted dependency root.
 */
public class Debinarizer implements TreeTransformer {

  private final TreeFactory tf;
  private final boolean forceCNF;
  private final TreeTransformer boundaryRemover;


  protected Tree transformTreeHelper(Tree t) {
    if (t.isLeaf()) {
      Tree leaf = tf.newLeaf(t.label());
      leaf.setScore(t.score());
      return leaf;
    }
    List newChildren = new ArrayList<>();
    for (int childNum = 0, numKids = t.numChildren(); childNum < numKids; childNum++) {
      Tree child = t.getChild(childNum);
      Tree newChild = transformTreeHelper(child);
      if ((!newChild.isLeaf()) && newChild.label().value().indexOf('@') >= 0) {
        newChildren.addAll(newChild.getChildrenAsList());
      } else {
        newChildren.add(newChild);
      }
    }
    Tree node = tf.newTreeNode(t.label(), newChildren);
    node.setScore(t.score());
    return node;
  }

  @Override
  public Tree transformTree(Tree t) {
    Tree result = transformTreeHelper(t);
    if (forceCNF) {
      result = new CNFTransformers.FromCNFTransformer().transformTree(result);
    }
    return boundaryRemover.transformTree(result);
  }

  public Debinarizer(boolean forceCNF) {
    this(forceCNF, CoreLabel.factory());
  }

  public Debinarizer(boolean forceCNF, LabelFactory lf) {
    this.forceCNF = forceCNF;
    tf = new LabeledScoredTreeFactory(lf);
    boundaryRemover = new BoundaryRemover();
  }

} // end class Debinarizer