Package edu.stanford.nlp.pipeline

Examples of edu.stanford.nlp.pipeline.StanfordCoreNLP.annotate()

669
670
671
672
673
674
675
676
677
678
679
      props.setProperty("pos.model", posModelPath);
    }
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props, false);

    Redwood.log(Redwood.DBG, "Annotating text");
    pipeline.annotate(doc);
    Redwood.log(Redwood.DBG, "Done annotating text");

    Map<String, List<CoreLabel>> sents = new HashMap<String, List<CoreLabel>>();

    for (CoreMap s : doc.get(CoreAnnotations.SentencesAnnotation.class)) {
View Full Code Here
338
339
340
341
342
343
344
345
346
347
348
      // Process a file.  The pipeline will do tokenization, which
      // means it will split it into sentences as best as possible
      // with the tokenizer.
      List<Annotation> annotations = getAnnotations(tokenizer, inputFormat, filename, filterUnknown);
      for (Annotation annotation : annotations) {
        pipeline.annotate(annotation);

        for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
          System.out.println(sentence);
          outputTree(System.out, sentence, outputFormats);
        }
View Full Code Here
353
354
355
356
357
358
359
360
361
362
363
      // possible with the tokenizer.  Output will go to filename.out
      // for each file.
      for (String file : fileList.split(",")) {
        List<Annotation> annotations = getAnnotations(tokenizer, inputFormat, file, filterUnknown);
        for (Annotation annotation : annotations) {
          pipeline.annotate(annotation);

          FileOutputStream fout = new FileOutputStream(file + ".out");
          PrintStream pout = new PrintStream(fout);
          for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
            pout.println(sentence);
View Full Code Here
379
380
381
382
383
384
385
386
387
388
389
          break;
        }
        line = line.trim();
        if (line.length() > 0) {
          Annotation annotation = tokenizer.process(line);
          pipeline.annotate(annotation);
          for (CoreMap sentence : annotation.get(CoreAnnotations.SentencesAnnotation.class)) {
            outputTree(System.out, sentence, outputFormats);
          }
        } else {
          // Output blank lines for blank lines so the tool can be
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
//      annotation = new Annotation("I know Fred has acne.  And Wilma has breast cancer.");
      annotation = new Annotation("( ( five plus three plus four ) * 2 ) divided by three");

    }

    pipeline.annotate(annotation);

    // An Annotation is a Map and you can get and use the various analyses individually.
    out.println();
    // The toString() method on an Annotation just prints the text of the Annotation
    // But you can see what is in it with other methods like toShorterString()
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
    Annotation ann = new Annotation("Damelo");
    Properties props = new Properties();
    props.setProperty("annotators", "tokenize");
    props.setProperty("tokenize.language", "es");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    pipeline.annotate(ann);

    Iterator<String> it = spanishTokens.iterator();
    for (CoreLabel word : ann.get(CoreAnnotations.TokensAnnotation.class)) {
      assertEquals("Bung token in new CoreLabel usage", it.next(), word.get(CoreAnnotations.TextAnnotation.class));
    }
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
 
  private void modifyUsingCoreNLPNER(Annotation doc) {
    Properties ann = new Properties();
    ann.setProperty("annotators", "pos, lemma, ner");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(ann, false);
    pipeline.annotate(doc);
    for (CoreMap sentence : doc.get(CoreAnnotations.SentencesAnnotation.class)) {
      List<EntityMention> entities = sentence.get(MachineReadingAnnotations.EntityMentionsAnnotation.class);
      if (entities != null) {
        List<CoreLabel> tokens = sentence.get(CoreAnnotations.TokensAnnotation.class);
        for (EntityMention en : entities) {
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
    Properties props = PropertiesUtils.fromString("annotators=tokenize,ssplit,pos,depparse");
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);

    String text = "Chris and John went to the store.";
    Annotation document = new Annotation(text);
    pipeline.annotate(document);

    SemanticGraph ccProcessed = document.get(CoreAnnotations.SentencesAnnotation.class).get(0)
                                        .get(
                                            SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class);
    Collection<TypedDependency> dependencies = ccProcessed.typedDependencies();
View Full Code Here
103
104
105
106
107
108
109
110
111
112
113
    Properties props = new Properties();
    props.setProperty("annotators", "tokenize,ssplit,pos,lemma,depparse");
    String text = "Barack Obama, a Yale professor, is president.";
    Annotation document = new Annotation(text);
    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    pipeline.annotate(document);

    // Serialization should not bork.
    File tempfile = IOUtils.writeObjectToTempFile(document.get(CoreAnnotations.SentencesAnnotation.class), "temp");

    // Deserialization should not bork.
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.