edu.stanford.nlp.parser.nndep.demo.DependencyParserDemo 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.nndep.demo;

import edu.stanford.nlp.ling.HasWord;
import edu.stanford.nlp.ling.TaggedWord;
import edu.stanford.nlp.parser.nndep.DependencyParser;
import edu.stanford.nlp.process.DocumentPreprocessor;
import edu.stanford.nlp.tagger.maxent.MaxentTagger;
import edu.stanford.nlp.trees.GrammaticalStructure;
import edu.stanford.nlp.util.logging.Redwood;

import java.io.StringReader;
import java.util.List;

/**
 * Demonstrates how to first use the tagger, then use the NN dependency
 * parser. Note that the parser will not work on untagged text.
 *
 * @author Jon Gauthier
 */
public class DependencyParserDemo  {

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

  public static void main(String[] args) {
    String modelPath = DependencyParser.DEFAULT_MODEL;
    String taggerPath = "edu/stanford/nlp/models/pos-tagger/english-left3words/english-left3words-distsim.tagger";

    for (int argIndex = 0; argIndex < args.length; ) {
      switch (args[argIndex]) {
        case "-tagger":
          taggerPath = args[argIndex + 1];
          argIndex += 2;
          break;
        case "-model":
          modelPath = args[argIndex + 1];
          argIndex += 2;
          break;
        default:
          throw new RuntimeException("Unknown argument " + args[argIndex]);
      }
    }

    String text = "I can almost always tell when movies use fake dinosaurs.";

    MaxentTagger tagger = new MaxentTagger(taggerPath);
    DependencyParser parser = DependencyParser.loadFromModelFile(modelPath);

    DocumentPreprocessor tokenizer = new DocumentPreprocessor(new StringReader(text));
    for (List sentence : tokenizer) {
      List tagged = tagger.tagSentence(sentence);
      GrammaticalStructure gs = parser.predict(tagged);

      // Print typed dependencies
      log.info(gs);
    }
  }

}