artinex.TypDep.java Source code

Introduction

Here is the source code for artinex.TypDep.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package artinex;

/**
 *
 * @author ashu
 */

import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.ling.Sentence;
import edu.stanford.nlp.parser.lexparser.LexicalizedParser;
import edu.stanford.nlp.parser.lexparser.Lexicon;
import edu.stanford.nlp.parser.lexparser.Options;
import edu.stanford.nlp.process.CoreLabelTokenFactory;
import edu.stanford.nlp.process.PTBTokenizer;
import edu.stanford.nlp.process.Tokenizer;
import edu.stanford.nlp.process.TokenizerFactory;
import edu.stanford.nlp.trees.GrammaticalStructure;
import edu.stanford.nlp.trees.GrammaticalStructureFactory;
import edu.stanford.nlp.trees.PennTreebankLanguagePack;
import edu.stanford.nlp.trees.Tree;
import edu.stanford.nlp.trees.TreeCoreAnnotations.TreeAnnotation;
import edu.stanford.nlp.trees.TreebankLanguagePack;
import edu.stanford.nlp.trees.TypedDependency;
import java.io.StringReader;
import java.util.Collection;
import java.util.List;

public class TypDep {

    private final static String PCG_MODEL = "edu/stanford/nlp/models/lexparser/englishPCFG.ser.gz";

    private final TokenizerFactory<CoreLabel> tokenizerFactory = PTBTokenizer.factory(new CoreLabelTokenFactory(),
            "invertible=true");

    private final LexicalizedParser parser = LexicalizedParser.loadModel(PCG_MODEL);

    public Tree parse(String str) {
        List<CoreLabel> tokens = tokenize(str);
        Tree tree = parser.apply(tokens);
        return tree;
    }

    private List<CoreLabel> tokenize(String str) {
        Tokenizer<CoreLabel> tokenizer = tokenizerFactory.getTokenizer(new StringReader(str));
        return tokenizer.tokenize();
    }

    public static void main(String[] args) {
        String str = "What is index in array";
        TypDep parser = new TypDep();
        Tree tree = parser.parse(str);

        List<Tree> leaves = tree.getLeaves();
        // Print words and Pos Tags
        for (Tree leaf : leaves) {
            Tree parent = leaf.parent(tree);
            System.out.print(leaf.label().value() + "-" + parent.label().value() + " ");
        }
        System.out.println();

        //Type dependencies

        // Tree tree1 = str.get(TreeAnnotation.class);
        // Get dependency tree
        TreebankLanguagePack tlp = new PennTreebankLanguagePack();
        GrammaticalStructureFactory gsf = tlp.grammaticalStructureFactory();
        GrammaticalStructure gs = gsf.newGrammaticalStructure(tree);
        Collection<TypedDependency> td = gs.typedDependenciesCollapsed();
        System.out.println(td);

    }

}