Examples of edu.stanford.nlp.parser.nndep.DependencyParser

edu.stanford.nlp.parser.nndep.DependencyParser

This class defines a transition-based dependency parser which makes use of a classifier powered by a neural network. The neural network accepts distributed representation inputs: dense, continuous representations of words, their part of speech tags, and the labels which connect words in a partial dependency parse.

This is an implementation of the method described in

Danqi Chen and Christopher Manning. A Fast and Accurate Dependency Parser Using Neural Networks. In EMNLP 2014.

New models can be trained from the command line; see {@link #main}for details on training options. This parser will also output CoNLL-X format predictions; again see {@link #main} for availableoptions.

This parser can also be used programmatically. The easiest way to prepare the parser with a pre-trained model is to call {@link #loadFromModelFile(String)}. Then call {@link #predict(edu.stanford.nlp.util.CoreMap)} on the returnedparser instance in order to get new parses. @author Danqi Chen (danqi@cs.stanford.edu) @author Jon Gauthier

    }


    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<HasWord> sentence : tokenizer) {
      List<TaggedWord> tagged = tagger.tagSentence(sentence);
      GrammaticalStructure gs = parser.predict(tagged);


      // Print typed dependencies
      System.err.println(gs);
    }
  }

Examples of edu.stanford.nlp.parser.nndep.DependencyParser

Related Classes of edu.stanford.nlp.parser.nndep.DependencyParser