`
sillycat
  • 浏览: 2477672 次
  • 性别: Icon_minigender_1
  • 来自: 成都
社区版块
存档分类
最新评论

TextExtract(3)NLP Token Name Finder

 
阅读更多
TextExtract(3)NLP Token Name Finder

All the models in http://opennlp.sourceforge.net/models-1.5/

For Name Finders, we have things as follow:

Date name finder model    en-ner-date.bin
Location name finder model    en-ner-location.bin
Money name finder model   en-ner-money.bin
Organization name finder model  en-ner-organization.bin
Percentage name finder model   en-ner-percentage.bin
Person name finder model     en-ner-person.bin
Time name finder model     en-ner-time.bin

package com.sillycat.resumeparse;

import java.io.IOException;
import java.io.InputStream;

import opennlp.tools.namefind.NameFinderME;
import opennlp.tools.namefind.TokenNameFinderModel;
import opennlp.tools.util.Span;

public class OpenNLPPersonNameMain {

public static void main(String[] args) {

String[] data = new String[] { "John", "Smith", "works", "for", "the",

"United", "Nations", "." };




InputStream modelIn = OpenNLPParserMain.class.getClassLoader()

.getResourceAsStream("models/en-ner-person.bin");




TokenNameFinderModel model = null;

try {

model = new TokenNameFinderModel(modelIn);


} catch (IOException e) {

e.printStackTrace();


} finally {

if (modelIn != null) {


try {



modelIn.close();




} catch (IOException e) {



e.printStackTrace();




}



}


}


NameFinderME tokenNameFinder = new NameFinderME(model);

Span[] spans = tokenNameFinder.find(data);

double[] probs = tokenNameFinder.probs();

for (int i = 0; i < spans.length; i++) {

int start = spans[i].getStart();


int end = spans[i].getEnd();


StringBuilder buffer = new StringBuilder();


for (int j = start; j < end; j++) {


buffer.append(data[j]);



if (j != (end - 1)) {



buffer.append(' ');




}



}


String value = buffer.toString();


System.out.println(value + " " + probs[i] + " ");


}


}

}

The results will be  John Smith 0.789394314903262

References:
http://sillycat.iteye.com/admin/blogs/2248952
分享到:
评论

相关推荐

Global site tag (gtag.js) - Google Analytics