Examples of edu.stanford.nlp.pipeline.Annotation

edu.stanford.nlp.pipeline.Annotation
An annotation representing a span of text in a document. Basically just an implementation of CoreMap that knows about text. You're meant to use the annotation keys in CoreAnnotations for common cases, but can define bespoke ones for unusual annotations. @author Jenny Finkel @author Anna Rafferty @author bethard

    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
    return pipeline;
  }


  private static void checkLabels(StanfordCoreNLP pipe, String text, String [] labels, String [] normed) {
    Annotation doc = new Annotation(text);
    pipe.annotate(doc);


    assertTrue(doc.get(CoreAnnotations.SentencesAnnotation.class) != null);
    assertTrue(doc.get(CoreAnnotations.SentencesAnnotation.class).size() > 0);
    CoreMap sent = doc.get(CoreAnnotations.SentencesAnnotation.class).get(0);
    assertTrue(sent.get(CoreAnnotations.TokensAnnotation.class) != null);
    List<CoreLabel> tokens = sent.get(CoreAnnotations.TokensAnnotation.class);
    if(VERBOSE){
      for(CoreLabel token: tokens) {
        System.out.println("\t" + token.word() + " " +

View Full Code Here


  /**
   * Given a list of sentences (as CoreMaps), wrap it in a new Annotation.
   */
  public static Annotation createDataset(List<CoreMap> sentences) {
    Annotation dataset = new Annotation("");
    addSentences(dataset,sentences);
    return dataset;
  }

View Full Code Here

  /**
   * Creates a deep copy of the given dataset with new lists for all mentions (entity, relation, event)
   * @param dataset
   */
  public static Annotation deepMentionCopy(CoreMap dataset) {
    Annotation newDataset = new Annotation("");


    List<CoreMap> sents = dataset.get(CoreAnnotations.SentencesAnnotation.class);
    List<CoreMap> newSents = new ArrayList<CoreMap>();
    if(sents != null){
      for(CoreMap sent: sents){

View Full Code Here

   * Deep copy of the sentence: we create new entity/relation/event lists here.
   * However,  we do not deep copy the ExtractionObjects themselves!
   * @param sentence
   */
  public static Annotation sentenceDeepMentionCopy(Annotation sentence) {
    Annotation newSent = new Annotation(sentence.get(CoreAnnotations.TextAnnotation.class));


    newSent.set(CoreAnnotations.TokensAnnotation.class, sentence.get(CoreAnnotations.TokensAnnotation.class));
    newSent.set(TreeCoreAnnotations.TreeAnnotation.class, sentence.get(TreeCoreAnnotations.TreeAnnotation.class));
    newSent.set(SemanticGraphCoreAnnotations.CollapsedDependenciesAnnotation.class, sentence.get(SemanticGraphCoreAnnotations.CollapsedDependenciesAnnotation.class));
    newSent.set(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class, sentence.get(SemanticGraphCoreAnnotations.BasicDependenciesAnnotation.class));
    newSent.set(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class, sentence.get(SemanticGraphCoreAnnotations.CollapsedCCProcessedDependenciesAnnotation.class));
    newSent.set(CoreAnnotations.DocIDAnnotation.class, sentence.get(CoreAnnotations.DocIDAnnotation.class));


    // deep copy of all mentions lists
    List<EntityMention> ents = sentence.get(MachineReadingAnnotations.EntityMentionsAnnotation.class);
    if(ents != null) newSent.set(MachineReadingAnnotations.EntityMentionsAnnotation.class, new ArrayList<EntityMention>(ents));
    List<RelationMention> rels = sentence.get(MachineReadingAnnotations.RelationMentionsAnnotation.class);
    if(rels != null) newSent.set(MachineReadingAnnotations.RelationMentionsAnnotation.class, new ArrayList<RelationMention>(rels));
    List<EventMention> evs = sentence.get(MachineReadingAnnotations.EventMentionsAnnotation.class);
    if(evs != null) newSent.set(MachineReadingAnnotations.EventMentionsAnnotation.class, new ArrayList<EventMention>(evs));


    return newSent;
  }

View Full Code Here

      .createExtractorFromFiles(
        TokenSequencePattern.getNewEnv(),
        rules);


    StanfordCoreNLP pipeline = new StanfordCoreNLP();
    Annotation annotation;
    if (args.length > 1) {
      annotation = new Annotation(IOUtils.slurpFileNoExceptions(args[1]));
    } else {
//      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()
    out.println("The top level annotation");
    out.println(annotation.toShorterString());
    List<CoreMap> sentences = annotation.get(CoreAnnotations.SentencesAnnotation.class);


    for (CoreMap sentence : sentences) {
      List<MatchedExpression> matchedExpressions = extractor
        .extractExpressions(sentence);
      for (MatchedExpression matched:matchedExpressions) {

View Full Code Here

    }
  }


  public void testCoref() throws IOException {
    String doc = IOUtils.slurpFile("edu/stanford/nlp/dcoref/STILLALONEWOLF_20050102.1100.eng.LDC2005E83.sgm");
    Annotation annotation = pipeline.process(doc);
    Map<Integer, CorefChain> chains = annotation.get(CorefCoreAnnotations.CorefChainAnnotation.class);
    Map<Integer, List<ExpectedMention>> expected = loadExpectedResults("edu/stanford/nlp/dcoref/STILLALONEWOLF_20050102.1100.eng.LDC2005E83.expectedcoref");
    compareResults(expected, chains);
  }

View Full Code Here

    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);


    // for example
    // "edu/stanford/nlp/dcoref/STILLALONEWOLF_20050102.1100.eng.LDC2005E83.sgm"
    String doc = IOUtils.slurpFile(input);
    Annotation annotation = pipeline.process(doc);
    Map<Integer, CorefChain> chains = annotation.get(CorefCoreAnnotations.CorefChainAnnotation.class);
    saveResults(output, chains);
  }

View Full Code Here

  public static String excelify(String s) {
    return '"'+s.replace("\"","\"\"")+'"';
  }


  public static List<CoreMap> readSentencesFromFile(String path) throws IOException, ClassNotFoundException {
    Annotation doc = (Annotation) IOUtils.readObjectFromFile(path);
    return doc.get(CoreAnnotations.SentencesAnnotation.class);


  }

View Full Code Here

   *
   * @throws SUTimeParsingError if anything goes wrong
   */
  public static Temporal parse(String str) throws SUTimeParsingError {
    try {
      Annotation doc = new Annotation(str);
      pipeline.annotate(doc);


      assert doc.get(CoreAnnotations.SentencesAnnotation.class) != null;
      assert doc.get(CoreAnnotations.SentencesAnnotation.class).size() > 0;
      List<CoreMap> timexAnnotations = doc.get(TimeAnnotations.TimexAnnotations.class);
      if (timexAnnotations.size() > 1) {
        throw new RuntimeException("Too many timexes for '" + str + "'");
      }
      CoreMap timex = timexAnnotations.get(0);

View Full Code Here

      "Da",
      "me",
      "lo");


  public void testSpanish() {
    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));
    }
    assertFalse("Too few tokens in new CoreLabel usage", it.hasNext());
  }

View Full Code Here

0 1 2 3 4 5

TOP

Related Classes of edu.stanford.nlp.pipeline.Annotation

com.lulu.WordCloud.StanfordLemmatizer

com.music.service.text.SentimentAnalyzer

edu.stanford.nlp.dcoref.ACEMentionExtractor

edu.stanford.nlp.dcoref.CoNLL2011DocumentReader

edu.stanford.nlp.dcoref.CoNLL2011DocumentReader$DocumentIterator

edu.stanford.nlp.dcoref.CoNLLMentionExtractor

edu.stanford.nlp.dcoref.DcorefExactOutputITest

edu.stanford.nlp.dcoref.MUCMentionExtractor

edu.stanford.nlp.dcoref.RuleBasedCorefMentionFinder

edu.stanford.nlp.dcoref.SieveCoreferenceSystem

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.