edu.stanford.nlp.trees.UniversalPOSMapper 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; 
import edu.stanford.nlp.util.logging.Redwood;

import java.io.IOException;
import java.util.List;

import edu.stanford.nlp.trees.tregex.TregexPattern;
import edu.stanford.nlp.trees.tregex.TregexPatternCompiler;
import edu.stanford.nlp.trees.tregex.tsurgeon.Tsurgeon;
import edu.stanford.nlp.trees.tregex.tsurgeon.TsurgeonPattern;
import edu.stanford.nlp.util.Pair;

/**
 * Helper class to perform a context-sensitive mapping of POS
 * tags in a tree to universal POS tags.
 *
 * @author Sebastian Schuster
 */

public class UniversalPOSMapper  {

  /** A logger for this class */
  private static Redwood.RedwoodChannels log = Redwood.channels(UniversalPOSMapper.class);

  public static final String DEFAULT_TSURGEON_FILE = "edu/stanford/nlp/models/upos/ENUniversalPOS.tsurgeon";

  private static boolean loaded = false;

  private static List> operations = null;

  private UniversalPOSMapper() {} // static methods

  public static void load() {
    load(DEFAULT_TSURGEON_FILE);
  }

  public static void load(String filename) {
    loaded = true;

    try {
      operations = Tsurgeon.getOperationsFromFile(filename, "UTF-8", new TregexPatternCompiler());
    } catch (IOException e) {
      System.err.printf("%s: Warning - could not load Tsurgeon file from %s.%n",
          UniversalPOSMapper.class.getSimpleName(), filename);
    }

  }

  public static Tree mapTree(Tree t) {
    if (!loaded) {
      load();
    }

    if (operations == null) {
      return t;
    }

    return Tsurgeon.processPatternsOnTree(operations, t.deepCopy());
  }

}