Last active
November 25, 2016 17:29
-
-
Save zawhtutwin/13f0c13bf99c93c4af957890d74488b5 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import java.io.File; | |
import java.io.FileInputStream; | |
import java.io.IOException; | |
import java.io.InputStream; | |
import opennlp.tools.namefind.NameFinderME; | |
import opennlp.tools.namefind.TokenNameFinderModel; | |
import opennlp.tools.tokenize.Tokenizer; | |
import opennlp.tools.tokenize.TokenizerME; | |
import opennlp.tools.tokenize.TokenizerModel; | |
import opennlp.tools.util.Span; | |
public class NameFinderTest { | |
static String sentence = "Mya Mya is Shan. Mg Mg is Burmese. Hla Hla is Kachin."; | |
//opennlp TokenNameFinderTrainer -model mm-ner-log.bin -lang en -data cities.txt -encoding UTF-8 | |
public static void main(String[] args) { | |
InputStream modelIn = null; | |
try { | |
InputStream is = new FileInputStream("E:\\opennlp\\bin\\en-token.bin"); | |
TokenizerModel tmodel = new TokenizerModel(is); | |
Tokenizer tokenizer = new TokenizerME(tmodel); | |
//Tokenizer tokenizer = SimpleTokenizer.INSTANCE; | |
TokenNameFinderModel model = new TokenNameFinderModel(new File("E:\\opennlp\\bin\\mm-ner-log.bin")); | |
NameFinderME nameFinder = new NameFinderME(model); | |
String tokens[] = tokenizer.tokenize(sentence); | |
Span nameSpans[] = nameFinder.find(tokens); | |
double[] spanProbs = nameFinder.probs(nameSpans); | |
for( int i = 0; i<nameSpans.length; i++) { | |
System.out.println("Span: "+nameSpans[i].toString()); | |
try{ | |
System.out.println(tokens[nameSpans[i].getEnd()+1]); | |
}catch(java.lang.ArrayIndexOutOfBoundsException ex){ | |
System.out.println(tokens[nameSpans[i].getEnd()]); | |
} | |
System.out.println("Probability is: "+spanProbs[i]); | |
System.out.println(); | |
} | |
} | |
catch (Exception ex) { | |
ex.printStackTrace(); | |
} | |
finally { | |
try { if (modelIn != null) modelIn.close(); } catch (IOException e){}; | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment