edu.stanford.nlp.trees.international.tuebadz.TueBaDZTreeReaderFactory 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.trees.international.tuebadz;

import java.io.Serializable;
import java.io.Reader;
import java.util.*;

import edu.stanford.nlp.trees.*;
import edu.stanford.nlp.ling.StringLabelFactory;


/** @author Christopher Manning */
public class TueBaDZTreeReaderFactory implements TreeReaderFactory, Serializable {

  private static final long serialVersionUID = 1614799885744961795L;

  private TreebankLanguagePack tlp;
  private int nodeCleanup;

  public TueBaDZTreeReaderFactory(TreebankLanguagePack tlp) {
    this(tlp, 0);
  }

  public TueBaDZTreeReaderFactory(TreebankLanguagePack tlp, int nodeCleanup) {
    this.tlp = tlp;
    this.nodeCleanup = nodeCleanup;
  }

  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);
  }

} // end class TueBaDZTreeReaderFactory