Nlp SBD 文本断句 包含中文 和英文断句

根据目前学习，中文断句  standford nlp可以实现中文分词和断句，下面有不同api的例子，大家可以试试

package com.example.utils;

import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.StringReader;
import java.nio.charset.Charset;
import java.util.List;

import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.process.CoreLabelTokenFactory;
import edu.stanford.nlp.process.PTBTokenizer;
import edu.stanford.nlp.process.WordToSentenceProcessor;
import edu.stanford.nlp.util.CoreMap;
import opennlp.tools.sentdetect.SentenceDetectorEvaluator;
import opennlp.tools.sentdetect.SentenceDetectorME;
import opennlp.tools.sentdetect.SentenceModel;
import opennlp.tools.sentdetect.SentenceSample;
import opennlp.tools.sentdetect.SentenceSampleStream;
import opennlp.tools.util.MarkableFileInputStreamFactory;
import opennlp.tools.util.ObjectStream;
import opennlp.tools.util.PlainTextByLineStream;
import opennlp.tools.util.Span;
import opennlp.tools.util.TrainingParameters;

/**  
 * Filename:    NlpSBD.java  
 * Description:   语句边界消岐 sentence boundary disambiguation
 * Copyright:   Copyright (c) 2019 All Rights Reserved.
 * @author:     wangk
 * @version:    1.0
 * Create at:   2019年5月7日 上午9:26:36  
 *  
 * Modification History:  
 * Date         Author      Version     Description  
 * ------------------------------------------------------------------  
 * 2019年5月7日      wangk      1.0         1.0 Version  
 *
*/

public class NlpSBD {
	
	//除了NLP API 外，还有java类有两个方法可以用，试用简单的文本断句，1使用正则2，使用breakIterator类，可以搜索一下
	static String paragraph =  "A simple approach to create a class to hold and remove stopwords. Let's IBM. this is a cat.";
	static String chineseLanguage = "第一个括号子表达式捕获 Web 地址的协议部分。 该子表达式匹配在冒号和两个正斜杠前面的任何单词。";
	
	public static void main(String[] args) {
		NlpSBD ns = new NlpSBD();
		//ns.sentDetect(paragraph);
		//ns.trainText();
		//System. out .println( " 内存信息 :" + toMemoryInfo ());
		ns.StanfordCoreNLP(chineseLanguage);
		
		
	}
	
	
	  /**  
     * 获取当前 jvm 的内存信息  
     *  
     * @return  
     */   
   public static String toMemoryInfo() {   
      Runtime currRuntime = Runtime.getRuntime ();   
      int nFreeMemory = ( int ) (currRuntime.freeMemory() / 1024 / 1024);   
      int nTotalMemory = ( int ) (currRuntime.totalMemory() / 1024 / 1024);   
      return nFreeMemory + "M/" + nTotalMemory + "M(free/total)" ;   
   }  


	/**
	 * @Description: