edu.stanford.nlp.parser.lexparser.ChineseLexicon 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 edu.stanford.nlp.util.Index;


/**
 * A lexicon class for Chinese.  Extends the (English) BaseLexicon class,
 * overriding its score and train methods to include a
 * ChineseUnknownWordModel.
 *
 * @author Roger Levy
 */
public class ChineseLexicon extends BaseLexicon {

  private static final long serialVersionUID = -7836464391021114960L;

  public final boolean useCharBasedUnknownWordModel;
  // public static final boolean useMaxentUnknownWordModel;
  public final boolean useGoodTuringUnknownWordModel;

  //private ChineseUnknownWordModel unknown;
  // private ChineseMaxentLexicon cml;
  private static final int STEPS = 1;
  private RandomWalk probRandomWalk;


  public ChineseLexicon(Options op, ChineseTreebankParserParams params, Index wordIndex, Index tagIndex) {
    super(op, wordIndex, tagIndex);
    useCharBasedUnknownWordModel = params.useCharBasedUnknownWordModel;
    useGoodTuringUnknownWordModel = params.useGoodTuringUnknownWordModel;
    // if (useMaxentUnknownWordModel) {
    //  cml = new ChineseMaxentLexicon();
    // } else {
    //unknown = new ChineseUnknownWordModel();
    //this.setUnknownWordModel(new ChineseUnknownWordModel(op));
    // this.getUnknownWordModel().setLexicon(this);
    // }
  }



  @Override
  public float score(IntTaggedWord iTW, int loc, String word, String featureSpec) {
    double c_W = seenCounter.getCount(iTW);
    boolean seen = (c_W > 0.0);

    if (seen) {
      return super.score(iTW, loc, word, featureSpec);
    } else {
      float score;
      // if (useMaxentUnknownWordModel) {
      //  score = cml.score(iTW, 0);
      // } else {
      score = this.getUnknownWordModel().score(iTW, loc, 0.0, 0.0, 0.0, word); // ChineseUnknownWordModel doesn't use the final three params
      // }
      return score;
    }
  }
}