Examples of BaseToken

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
      List<BaseToken> tokens = JCasUtil.selectCovered(jCas, BaseToken.class, sentence);
      DepTree tree = new DepTree();

      // Convert CAS data into structures usable by ClearParser
      for (int i = 0; i < tokens.size(); i++) {
        BaseToken token = tokens.get(i);
        DepNode node = new DepNode();
        node.id = i + 1;
        node.form = token.getCoveredText();
        node.pos = token.getPartOfSpeech();
        node.lemma = useLemmatizer ? lemmatizer.getLemma(node.form, node.pos) : token.getNormalizedForm();
        tree.add(node);
      }

      // Run parser and convert output back to CAS friendly data types
      parser.parse(tree);
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

48
49
50
51
52
53
54
55
56
57
    // index the base tokens and NEs by their offsets
    hbs = new Hashtable<Integer, BaseToken>();
    hbe = new Hashtable<Integer, BaseToken>();
    FSIterator iter = jcas.getJFSIndexRepository().getAnnotationIndex(BaseToken.type).iterator();
    while (iter.hasNext()) {
      BaseToken t = (BaseToken) iter.next();
      hbs.put(t.getBegin(), t);
      hbe.put(t.getEnd(), t);
    }
  }
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

60
61
62
63
64
65
66
67
68
69
70
    stopwords = l;
  }

  static boolean isPronoun (Markable m) {
    if (m.getContent() instanceof BaseToken) {
      BaseToken t = (BaseToken) m.getContent();
      if (t.getPartOfSpeech().startsWith("PRP")) // TODO: since only 3rd person pronouns are added as markables, no need to check
        return true;
    }
    return false;
  }
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
    return "U";
  }

  public ArrayList<BaseToken> containedTokens (int a, int b) {
    ArrayList<BaseToken> ret = new ArrayList<BaseToken>();
    BaseToken t1 = hbs.get(a);
    BaseToken t2 = hbe.get(b);
    if (t1!=null && t2!=null) {
      int begin = t1.getTokenNumber();
      int end = t2.getTokenNumber();
      LinkedList<Annotation> l = FSIteratorToList.convert(jcas.getJFSIndexRepository().getAnnotationIndex(BaseToken.type).iterator());
      for (int i = 0; i < l.size(); i++) {
        BaseToken t = (BaseToken) l.get(i);
        if (t.getTokenNumber()>=begin && t.getTokenNumber()<=end)
          ret.add(t);
      }
    }
//    int e;
//    while (t!=null && (e=t.getEnd())<=b) {
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

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
                }
            }

            ListIterator<BaseToken> itt           = tokens.listIterator();
            ListIterator<ConllDependencyNode> itn = nodes.listIterator();
            BaseToken           bt = null;
            ConllDependencyNode dn = null;
            if (tokens.size()>0 && nodes.size()>0) {
                // iterate through the parallel sorted lists
              if (itt.hasNext()) bt                  = itt.next();
              if (itn.hasNext()) dn                  = itn.next();
              if (dn != null)
                if (dn.getId()==0 && itn.hasNext())
                  dn = itn.next();
              while (itt.hasNext() || itn.hasNext()) {
                if (bt.getBegin()==dn.getBegin() && bt.getEnd()==dn.getEnd()) {
                  dn.setPostag( bt.getPartOfSpeech() );
                  dn.setCpostag( bt.getPartOfSpeech() ); 
                  dn.addToIndexes();
                  if (itt.hasNext()) bt = itt.next();
                  if (itn.hasNext()) dn = itn.next();
                } else if ( bt.getBegin()<dn.getBegin() ) {
                  if (itt.hasNext()) bt = itt.next(); else break;
                } else if ( bt.getBegin()>dn.getBegin() ) {
                  if (itn.hasNext()) dn = itn.next(); else break;
                }
              }
              if (bt.getBegin()==dn.getBegin() && bt.getEnd()==dn.getEnd()) {
                dn.setPostag( bt.getPartOfSpeech() );
                dn.setCpostag( bt.getPartOfSpeech() ); 
                dn.addToIndexes();
              }
            }
             
    }
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator btaItr = indexes.getAnnotationIndex(BaseToken.type).iterator();
    while (btaItr.hasNext())
    {
      BaseToken bta = (BaseToken) btaItr.next();
      if (!((bta instanceof NewlineToken)
          || (bta instanceof PunctuationToken)
          || (bta instanceof ContractionToken)
          || (bta instanceof SymbolToken)))
      {
        LookupToken lt = new LookupAnnotationToJCasAdapter(bta);

        // POS exclusion logic for first word lookup
        if (isTagExcluded(bta.getPartOfSpeech()))
        {
          lt.addStringAttribute(
              FirstTokenPermutationImpl.LT_KEY_USE_FOR_LOOKUP,
              "false");
        }
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

75
76
77
78
79
80
81
82
83
84
85
    JFSIndexRepository indexes = jcas.getJFSIndexRepository();
    Iterator btaItr = indexes.getAnnotationIndex(BaseToken.type)
        .iterator();
    while (btaItr.hasNext())
    {
      BaseToken bta = (BaseToken) btaItr.next();
      if (!((bta instanceof NewlineToken)
          || (bta instanceof PunctuationToken)
          || (bta instanceof ContractionToken)
          || (bta instanceof SymbolToken)))
      {
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
        //add segment ID as a features:
        features.add(new Feature("SegmentID", segment.getId()));

        // features from dominating parse tree
        //        for(SimpleFeatureExtractor extractor : this.parseFeatureExtractors){
        BaseToken startToken = token;
        for(int i = tokenIndex-1; i >= 0; --i){
          String outcome = outcomes.get(i);
          if(outcome.equals("O")){
            break;
          }
          startToken = tokens.get(i);
        }
        features.addAll(parseExtractor.extract(jCas, startToken.getBegin(), token.getEnd()));
        //        }
       
        // apply feature selection, if necessary
            if (this.featureSelection != null) {
              features = this.featureSelection.transform(features);
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

116
117
118
119
120
121
122
123
124
125
126
  public List<Feature> extract(JCas view, Annotation annotation) throws CleartkExtractorException {

    Map<BaseToken, Collection<IdentifiedAnnotation>> coveringMap =
        JCasUtil.indexCovering(view, BaseToken.class, IdentifiedAnnotation.class);

    BaseToken targetTokenAnnotation = (BaseToken)annotation;

    Collection<IdentifiedAnnotation> idannoList = coveringMap.get(targetTokenAnnotation);

    ArrayList<Feature> features = new ArrayList<Feature>();
View Full Code Here

Examples of org.apache.ctakes.typesystem.type.syntax.BaseToken

141
142
143
144
145
146
147
148
149
150
151
152
153
154
//        if (baseTokenAnnotationUntyped.getBegin() < sentenceBegin ||
//            baseTokenAnnotationUntyped.getEnd() > sentenceEnd)
//        {
//          continue;
//        }
        BaseToken baseToken = (BaseToken)baseTokenAnnotationUntyped;
        if (!(baseToken instanceof NewlineToken))
        {
          String currentTokenText = baseToken.getCoveredText();
          arrayOfTokens.add(currentTokenText);
        }
      }
      arrayOfLines.add(arrayOfTokens);
     
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.