Java 开放式NLP NER未经过适当培训
我尝试使用openNlp为NER训练一个自定义模型。当我传递一个句子来预测实体时，它只选择句子的第一个单词。不知道我哪里出错了 请在下面查找培训型号代码Java 开放式NLP NER未经过适当培训,java,opennlp,Java,Opennlp,我尝试使用openNlp为NER训练一个自定义模型。当我传递一个句子来预测实体时，它只选择句子的第一个单词。不知道我哪里出错了 请在下面查找培训型号代码 public class OpenNLPNER { public static void main(String[] args) { train("en", "technology", "D:\\dl4j-examples-master\\dl4j-examples-master\\dl4j-examples\\src\
public class OpenNLPNER {
public static void main(String[] args) {
train("en", "technology", "D:\\dl4j-examples-master\\dl4j-examples-master\\dl4j-examples\\src\\main\\java\\opennlpExamples\\src\\main\\resources\\technology.train", "D:\\dl4j-examples-master\\dl4j-examples-master\\dl4j-examples\\src\\main\\java\\opennlpExamples\\src\\main\\techno1.bin");
}
public static String train(String lang, String entity, InputStreamFactory inputStream, FileOutputStream modelStream) {
Charset charset = Charset.forName("UTF-8");
TokenNameFinderModel model = null;
ObjectStream<NameSample> sampleStream = null;
try {
ObjectStream<String> lineStream = new PlainTextByLineStream(inputStream, charset);
sampleStream = new NameSampleDataStream(lineStream);
TokenNameFinderFactory nameFinderFactory = new TokenNameFinderFactory();
model = NameFinderME.train("en", "technology", sampleStream, TrainingParameters.defaultParams(),
nameFinderFactory);
} catch (FileNotFoundException fio) {
} catch (IOException io) {
} finally {
try {
sampleStream.close();
} catch (IOException io) {
}
}
BufferedOutputStream modelOut = null;
try {
modelOut = new BufferedOutputStream(modelStream);
model.serialize(modelOut);
} catch (IOException io) {
} finally {
if (modelOut != null) {
try {
modelOut.close();
} catch (IOException io) {
}
}
}
return "Something goes wrong with training module.";
}
public static String train(String lang, String entity, String taggedCoprusFile,
String modelFile) {
try {
InputStreamFactory inputStream = new InputStreamFactory() {
FileInputStream fileInputStream = new FileInputStream("D:\\dl4j-examples-master\\dl4j-examples-master\\dl4j-examples\\src\\main\\java\\opennlpExamples\\src\\main\\resources\\technology.train");
public InputStream createInputStream() throws IOException {
return fileInputStream;
}
};
// InputStreamFactory temp= new InputStream("D:\\dl4j-examples-master\\dl4j-examples-master\\dl4j-examples\\src\\main\\java\\opennlpExamples\\src\\main\\resources\\en-ner-medical.train") ;
return train(lang, entity, inputStream,
new FileOutputStream(modelFile));
} catch (Exception e) {
e.printStackTrace();
}
return "Something goes wrong with training module.";
}
}
public class nameEntity {
public static void main(String[] args) throws Exception {
InputStream modelIn = new FileInputStream( "D:/main/techno.bin");
InputStream tokenModelIn = new FileInputStream( "C:/openNLP/en-
token.bin");
try {
TokenNameFinderModel model = new TokenNameFinderModel(modelIn);
NameFinderME nameFinder = new NameFinderME(model);
//Instantiating the NameFinder class
//nameFinder = new NameFinderME(model);
TokenizerModel tokenModel = new TokenizerModel(tokenModelIn);
//Instantiating the TokenizerME class
TokenizerME tokenizer = new TokenizerME(tokenModel);
//Getting the sentence in the form of String array
String sentence = "Camel is a Java software";
String tokens[] = tokenizer.tokenize(sentence);
//Finding the names in the sentence
nameFinder.clearAdaptiveData();
Span nameSpans[] = nameFinder.find(tokens);
System.out.println(sentence);
//Printing the spans of the names in the sentence
for(Span s: nameSpans) {
System.out.println(s.toString()+" "+tokens[s.getStart()]);
}
}
}
提前感谢。Empty
catchcatch