Java Code Examples for edu.stanford.nlp.pipeline.StanfordCoreNLP#process()

The following examples show how to use edu.stanford.nlp.pipeline.StanfordCoreNLP#process() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: Chapter3.java    From Natural-Language-Processing-with-Java-Second-Edition with MIT License 6 votes vote down vote up 
private static void usingStanfordPipeline() {
        Properties properties = new Properties();
        properties.put("annotators", "tokenize, ssplit");
        StanfordCoreNLP pipeline = new StanfordCoreNLP(properties);
        Annotation annotation = new Annotation(paragraph);
        pipeline.annotate(annotation);
        pipeline.prettyPrint(annotation, System.out);
//        try {
//            pipeline.xmlPrint(annotation, System.out);
//        } catch (IOException ex) {
//            ex.printStackTrace();
//        }
        Annotation a = pipeline.process(paragraph);
        System.out.println("----------");
        System.out.println(a.size());
        System.out.println("----------");
        System.out.println(annotation);
        System.out.println("----------");
        System.out.println(annotation.toShorterString("NN"));
//        TreePrint treePrint = pipeline.getConstituentTreePrinter();
//        treePrint = pipeline.getDependencyTreePrinter();
//        treePrint.printTree(new SimpleTree());
    }
Example 2
Source File: Postprocess.java    From phrases with Apache License 2.0 6 votes vote down vote up 
public List<Pattern> run(List<Pattern> patterns) {

        Properties props = new Properties();
        props.setProperty("annotators", "tokenize, ssplit, pos, lemma, parse, sentiment");
        StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

        for (Pattern pattern : patterns) {
            Annotation annotation = pipeline.process(pattern.toSentences());
            for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
                    Tree tree = sentence.get(SentimentCoreAnnotations.AnnotatedTree.class);
                    int sentiment = RNNCoreAnnotations.getPredictedClass(tree);
                    for (CoreLabel token : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
                        String lemma = token.get(CoreAnnotations.LemmaAnnotation.class);

                    }
            }
        }
        return null;
    }
Example 3
Source File: Extract.java    From phrases with Apache License 2.0 5 votes vote down vote up 
public List<Pattern> run(String text) {
    List<Pattern> patterns = new ArrayList<Pattern>();

    Properties props = new Properties();
    props.setProperty("annotators", "tokenize, ssplit, pos, parse");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    Annotation annotation = pipeline.process(text);
    List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);
    for (CoreMap sentence : sentences) {
        patterns.addAll(ExtractSentencePatterns(sentence));
    }

    return patterns;
}
Example 4
Source File: CoreNLPToJSON.java    From phrasal with GNU General Public License v3.0 4 votes vote down vote up 
/**
 * Process an English text file.
 * 
 * @param args
 * @throws IOException 
 */
public static void main(String[] args) throws IOException {
  if (args.length < 1) {
    System.err.printf("Usage: java %s file [inputproperties_str] > json_output%n", CoreNLPToJSON.class.getName());
    System.exit(-1);
  }
  String textFile = args[0];
  InputProperties inputProperties = args.length > 1 ? InputProperties.fromString(args[1]) : new InputProperties();

  StanfordCoreNLP coreNLP = new StanfordCoreNLP(properties);
  
  // Configure tokenizer
  EnglishPreprocessor preprocessor = new EnglishPreprocessor(true);
  
  // Use a map with ordered keys so that the output is ordered by segmentId.
  Map<Integer,SourceSegment> annotations = new TreeMap<Integer,SourceSegment>();
  LineNumberReader reader = IOTools.getReaderFromFile(textFile);
  for (String line; (line = reader.readLine()) != null;) {
    Annotation annotation = coreNLP.process(line);
    List<CoreMap> sentences = annotation.get(SentencesAnnotation.class);
    if (sentences.size() != 1) {
      throw new RuntimeException("Sentence splitting on line: " + String.valueOf(reader.getLineNumber()));
    }
    CoreMap sentence = sentences.get(0);
    Tree tree = sentence.get(TreeAnnotation.class);
    tree.indexLeaves();
    int[] chunkVector = getChunkVector(tree);
    List<CoreLabel> tokens = sentence.get(TokensAnnotation.class);
    int numTokens = tokens.size();
    SymmetricalWordAlignment alignment = preprocessor.processAndAlign(line);
    if (alignment.e().size() != numTokens) {
      throw new RuntimeException(String.format("Tokenizer configurations differ: %d/%d", alignment.e().size(), numTokens));
    }
    SourceSegment segment = new SourceSegment(numTokens);
    segment.layoutSpec.addAll(makeLayoutSpec(alignment));
    segment.inputProperties = inputProperties.toString();
    for (int j = 0; j < numTokens; ++j) {
      CoreLabel token = tokens.get(j);
      String word = token.get(TextAnnotation.class);
      segment.tokens.add(unescape(word));
      String pos = mapPOS(token.get(PartOfSpeechAnnotation.class));
      segment.pos.add(pos);
      String ne = token.get(NamedEntityTagAnnotation.class);
      segment.ner.add(ne);
      segment.chunkVector[j] = chunkVector[j];
    }
    annotations.put(reader.getLineNumber()-1, segment);
  }
  reader.close();
  System.err.printf("Processed %d sentences%n", reader.getLineNumber());
  
  final SourceDocument jsonDocument = new SourceDocument(textFile, annotations);
  
  // Convert to json
  Gson gson = new Gson();
  String json = gson.toJson(jsonDocument);
  System.out.println(json);
}