基于Stanford Parser 及OpenNLP Shallow Parser构建句子语法解析树

最近做一个项目需要对给定的文本中的句子做Parse，根据POS tag及句子成分信息找出词语/短语之间的dependency，然后根据dependency构建句子的parse tree. 需要用到Stanford Parser和OpenNLP 中的Shallow Parser，这两个Parser都用JAVA实现，提供API方式调用，可以根据句子输出语法解析树。下面总结两类Parser的作用及JAVA程序调用方法。

1 Shallow Parser

Shallow Parser主要作用是找出句子中的短语信息，包括名词短语NP，动词短语VP，形容词短语ADJP，副词短语ADVP等等，示例程序如下

package edu.pku.yangliu.nlp.pdt;

import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.StringReader;
import java.util.HashMap;

import opennlp.tools.chunker.ChunkerME;
import opennlp.tools.chunker.ChunkerModel;
import opennlp.tools.cmdline.PerformanceMonitor;
import opennlp.tools.cmdline.postag.POSModelLoader;
import opennlp.tools.postag.POSModel;
import opennlp.tools.postag.POSSample;
import opennlp.tools.postag.POSTaggerME;
import opennlp.tools.tokenize.WhitespaceTokenizer;
import opennlp.tools.util.InvalidFormatException;
import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.PlainTextByLineStream;

/**a Shallow Parser based on opennlp
 * @author yangliu
 * @blog http://blog.csdn.net/yangliuy
 * @mail yang.liu@pku.edu.cn
 */

public class ShallowParser {
	
	private static ShallowParser instance = null ;
	private static POSModel model;
	private static ChunkerModel cModel ;
	
	//Singleton pattern
	public static ShallowParser getInstance() throws InvalidFormatException, IOException{
		if(ShallowParser.instance == null){
			POSModel model = new POSModelLoader().load(new File("en-pos-maxent.bin"));
			InputStream is = new FileInputStream("en-chunker.bin");
			ChunkerModel cModel = new ChunkerModel(is);
			ShallowParser.instance = new ShallowParser(model, cModel);
		}
		return ShallowParser.instance;
	}
	
	public ShallowParser(POSModel model, ChunkerModel cModel){
		ShallowParser.model = model;
		ShallowParser.cModel = cModel;
		
	}
	
	 /** A shallow Parser, chunk a sentence and return a map for the phrase
	  *  labels of words <wordsIndex, phraseLabel>
	 *   Notice: There should be " " BEFORE and after ",", " ","(",")" etc.
	 * @param input The input sentence
	 * @param model The POSModel of the chunk
	 * @param cMode