Package gate

Examples of gate.AnnotationSet

60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
  private String dictionaryEncoding = "UTF-8";

  @Override
  public void execute() throws ExecutionException {
    // text doc annotations
    AnnotationSet annotations;
    if (annotationSetName != null && annotationSetName.length() > 0)
      annotations = document.getAnnotations(annotationSetName);
    else
      annotations = document.getAnnotations();

    // getdoc.get text
    String text = document.getContent().toString();

    // get sentence annotations
    AnnotationSet sentences = annotations.get("Sentence");

    // order sentences

    List<Annotation> sentList = new LinkedList<Annotation>();

    for (Iterator iterator = sentences.iterator(); iterator.hasNext();) {
      sentList.add((Annotation) iterator.next());

    }

    java.util.Collections.sort(sentList, new gate.util.OffsetComparator());

    // for each sentence get token annotations
    for (Iterator iterator = sentList.iterator(); iterator.hasNext();) {
      Annotation annotation = (Annotation) iterator.next();

      AnnotationSet sentenceTokens = annotations.get("Token", annotation
          .getStartNode().getOffset(), annotation.getEndNode()
          .getOffset());

      // create a list

      List<Annotation> tokenList = new LinkedList<Annotation>();

      for (Iterator iterator2 = sentenceTokens.iterator(); iterator2
          .hasNext();) {
        tokenList.add((Annotation) iterator2.next());

      }
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
  private List<NameFinder> finder;

  @Override
  public void execute() throws ExecutionException {
    // text doc annotations
    AnnotationSet annotations;
    if (inputASName != null && inputASName.length() > 0)
      annotations = document.getAnnotations(inputASName);
    else
      annotations = document.getAnnotations();

    AnnotationSet outputAnnots;
    if (outputASName != null && outputASName.length() > 0)
      outputAnnots = document.getAnnotations(outputASName);
    else
      outputAnnots = document.getAnnotations();
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
  URL model;

  @Override
  public void execute() throws ExecutionException {
    // text doc annotations
    AnnotationSet annotations;
    if (annotationSetName != null && annotationSetName.length() > 0)
      annotations = document.getAnnotations(annotationSetName);
    else
      annotations = document.getAnnotations();

    // get sentence annotations
    //AnnotationSet sentences = document.getAnnotations("Sentence");

    // getdoc.get text
    String text = document.getContent().toString();
    // run tokenizer
    Span[] spans = tokenizer.tokenizePos(text);
    // compare the resulting
    // spans and add annotations

    for (int i = 0; i < spans.length; i++) {

      FeatureMap fm = Factory.newFeatureMap();
      // type
      fm.put("source", "openNLP");
      fm.put("string", text.substring(spans[i].getStart(), spans[i]
          .getEnd()));
      // source
//      fm.put("type", "urn:lsid:ontotext.com:kim:iextraction:Token");

      try {
        annotations.add(Long.valueOf(spans[i].getStart()), Long
            .valueOf(spans[i].getEnd()), "Token", fm);

      } catch (InvalidOffsetException e) {
        e.printStackTrace();
        throw new RuntimeException(e);
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
  @Override
  public void execute() throws ExecutionException {
    boolean isSentenceSplitted = false;
    // text doc annotations
    AnnotationSet annotations;
    if (annotationSetName != null && annotationSetName.length() > 0)
      annotations = document.getAnnotations(annotationSetName);
    else
      annotations = document.getAnnotations();
    // getdoc.get text
    String text = document.getContent().toString();
    // run tokenizer
    int[] spans = splitter.sentPosDetect(text);
    // compare the resulting
    // sentences and add annotations
    int prevSpan = 0;
    for (int i = 0; i < spans.length; i++) {

      FeatureMap fm = Factory.newFeatureMap();
      // type
      fm.put("source", "openNLP");
      // source
      // fm.put("type", "urn:lsid:ontotext.com:kim:iextraction:Sentence");

      try {
        // annotations.add(Long.valueOf(spans[i].getStart()),
        // Long.valueOf(spans[i].getEnd()), "Sentence", fm);
        // annotations.add(i == 0 ? Long.valueOf(prevSpan) : Long
        // .valueOf(prevSpan + countSpaces(prevSpan - 1)),
        // i == (spans.length - 1) ? Long.valueOf(spans[i]) : Long
        // .valueOf(spans[i] - 1), "Sentence", fm);
        int start = prevSpan;
        int end = spans[i];

        // remove leading spaces of a sentence
        for (int j = start; j < end
            && Character.isWhitespace(text.charAt(j)); j++) {
          start = j + 1;
        }

        // remove trailing spaces of a sentence
        if (end > 1) {
          for (int j = end; j > start
              && Character.isWhitespace(text.charAt(j - 1)); j--) {
            end = j - 1;
          }
        }

        annotations.add(Long.valueOf(start), Long.valueOf(end),
            "Sentence", fm);
        if(!isSentenceSplitted)
          isSentenceSplitted = true;

      } catch (InvalidOffsetException e) {
        e.printStackTrace();
        throw new RuntimeException(e);
      }

      prevSpan = spans[i];
    }
    if(!isSentenceSplitted){
      FeatureMap fm = Factory.newFeatureMap();
      // type
      fm.put("source", "openNLP");
      try {
        annotations.add(new Long(0), new Long(text.length()),
            "Sentence", fm);
      } catch (InvalidOffsetException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
      }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
  @SuppressWarnings("unchecked")
  @Override
  public void execute() throws ExecutionException {
    // text doc annotations
    AnnotationSet annotations;
    if (annotationSetName != null && annotationSetName.length() > 0) {
      annotations = document.getAnnotations(annotationSetName);
    } else {
      annotations = document.getAnnotations();
    }

    // getdoc.get text
    // String text = document.getContent().toString();

    // get token and sentence annotations
    AnnotationSet sentences = annotations.get("Sentence");
    AnnotationSet tokensAS = annotations.get("Token");

    if (sentences != null && sentences.size() > 0 && tokensAS != null
        && tokensAS.size() > 0) {

      // order them
      List<Annotation> sentList = new LinkedList<Annotation>();

      for (Iterator iterator = sentences.iterator(); iterator.hasNext();) {
        sentList.add((Annotation) iterator.next());

      }

      java.util.Collections.sort(sentList,
          new gate.util.OffsetComparator());

      // for each sentence get token annotations
      for (Iterator iterator = sentList.iterator(); iterator.hasNext();) {
        Annotation annotation = (Annotation) iterator.next();

        AnnotationSet sentenceTokens = annotations.get("Token",
            annotation.getStartNode().getOffset(), annotation
                .getEndNode().getOffset());

        // create a list

        List<Annotation> annList = new LinkedList<Annotation>();

        for (Iterator<Annotation> iterator2 = sentenceTokens.iterator(); iterator2
            .hasNext();) {
          annList.add(iterator2.next());

        }

        // order on offset
        Collections.sort(annList, new gate.util.OffsetComparator());

        // make the array be string[] sentence
        String[] tokens = new String[sentenceTokens.size()];
        String[] postags = new String[sentenceTokens.size()];
        int i = 0;
        for (Iterator iterator3 = annList.iterator(); iterator3
            .hasNext();) {

          Annotation token = (Annotation) iterator3.next();
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
    String locType = "location";
    String orgType = "org";
    String perType = "person";

    // extract sentences from text
    AnnotationSet sentences = inputAS.get(sequenceType);
    ArrayList<Element<Object>> elements = new ArrayList<Element<Object>>();
    OffsetComparator oc = new OffsetComparator();
    SparseVector[] x;
    Object[] y;
    ElementSequence<Element<Object>> sequence;
    Element<Object> element;
    ArrayList<Annotation> tokens, dToks, lToks, oToks, pToks;
    AnnotationSet dats, locs, orgs, pers;
    String chunk, label;

    for (Annotation sentence : sentences) {

      //extract NEs from sentence
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
    pipeline.execute();
    Factory.deleteResource(corpus);
    Factory.deleteResource(pipeline);

    // extract sentences from text
    AnnotationSet sentences = inputAS.get(sequenceType);
    ArrayList<Element<Object>> elements = new ArrayList<Element<Object>>();
    OffsetComparator oc = new OffsetComparator();
    SparseVector[] x;
    Object[] y;
    ElementSequence<Element<Object>> sequence;
View Full Code Here
89
90
91
92
93
94
95
96
97
98
99
    pipeline.execute();
    Factory.deleteResource(corpus);
    Factory.deleteResource(pipeline);

    // extract sentences from text
    AnnotationSet sentences = inputAS.get(sequenceType);
    ArrayList<Element<Object>> elements = new ArrayList<Element<Object>>();
    Alphabet labelAlphabet = tagger.getYAlphabet();
    OffsetComparator oc = new OffsetComparator();
    SparseVector[] x;
    Object[] y;
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
    //specify noun and verb chunk types
    String nChunkType = "nchunk";
    String vChunkType = "vchunk";

    // extract sentences from text
    AnnotationSet sentences = inputAS.get(sequenceType);
    ArrayList<Element<Object>> elements = new ArrayList<Element<Object>>();
    OffsetComparator oc = new OffsetComparator();
    SparseVector[] x;
    Object[] y;
    ElementSequence<Element<Object>> sequence;
    Element<Object> element;
    ArrayList<Annotation> tokens, nToks, vToks;
    AnnotationSet nChunks, vChunks;
    String chunk, label;

    for (Annotation sentence : sentences) {

      //extract noun and verb chunks from sentence
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
  @SuppressWarnings("unchecked")
  public void extractData(String sequenceType, String elementType, String labelType)
  throws ExecutionException, InvalidOffsetException, ResourceInstantiationException {

    //extract tokens from text
    AnnotationSet tokens = inputAS.get(sequenceType);
    ArrayList<Element<Object>> elements = new ArrayList<Element<Object>>();
    ElementSequence<Element<Object>> sequence;
    SparseVector[] x;
    Object[] y;
    char[] chars;
View Full Code Here
TOP

Related Classes of gate.AnnotationSet

  • at.ofai.gate.japeutils.JapeUtils
  • at.ofai.gate.japeutils.ops.NotCoextensive
  • at.ofai.gate.japeutils.ops.NotEndsAt
  • at.ofai.gate.japeutils.ops.NotOverlaps
  • at.ofai.gate.japeutils.ops.NotStartsAt
  • at.ofai.gate.virtualdocuments.AnnotateBySpecPR
  • at.ofai.gate.virtualdocuments.AnnotatedDocumentTransformer
  • at.ofai.gate.virtualdocuments.CopyVirtualDocumentPR
  • at.ofai.gate.virtualdocuments.ExportContainedAnnotationsPR
  • at.ofai.gate.virtualdocuments.FeatureLanguageAnalyserPR
    • Copyright © 2018 www.massapicom. 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.