Package org.apache.ctakes.typesystem.type.syntax

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

163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
                  sentEnd   = sentStart;
                  for (String aline : lines) {
                      sentEnd += aline.split("\t")[1].length()+1;
                  }
                  if ( !inputFormat.contains("tok") ) {
                      depNodes.add( new ConllDependencyNode(jCas,sentStart,sentEnd));
                      depNodes.get(depNodes.size()-1).setId(0);
                      depNodes.get(depNodes.size()-1).addToIndexes(jCas);
                  }

                  /** Create tokens */
                  if ( inputFormat.contains("tok") ) {
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.addToIndexes();
                          documentText.append(tokens[1] + " ");
                          wordStart = wordEnd+1;
                      }
                  } else if ( inputFormat.contains("min") ) {
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          if (trainingMode)
                            depNodes.add( new ConllDependencyNode(jCas,wordStart,wordEnd) );
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.addToIndexes();
                          documentText.append(tokens[1] + " ");
                          wordStart = wordEnd+1;
                      }
                  } else if ( inputFormat.contains("mpos")) {
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          if (trainingMode)
                            depNodes.add( new ConllDependencyNode(jCas,wordStart,wordEnd) );
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.setPartOfSpeech(tokens[2]);
                          btoken.addToIndexes();
                          documentText.append(tokens[1] + " ");
                          wordStart = wordEnd+1;
                      }
                  } else if ( inputFormat.contains("mlem")) {
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          if (trainingMode)
                            depNodes.add( new ConllDependencyNode(jCas,wordStart,wordEnd) );
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.setNormalizedForm(tokens[2]);
                          btoken.addToIndexes();
                          documentText.append(tokens[1] + " ");
                          wordStart = wordEnd+1;
                      }
                  } else if ( inputFormat.contains("dep")) {
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          if (trainingMode)
                            depNodes.add( new ConllDependencyNode(jCas,wordStart,wordEnd) );
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.setNormalizedForm(tokens[2]);
                          btoken.setPartOfSpeech(tokens[3]);
                          btoken.addToIndexes();
                          documentText.append(tokens[1] + " ");
                          wordStart = wordEnd+1;
                      }
                  } else { // CONLL format assumed
                      if (!inputFormat.contains("conll")) { System.err.println("Warning: Assuming CONLL-x input format"); }
                      for (String aline : lines) {                   
                          String[] tokens = aline.split("\t");
                          wordEnd = wordStart + tokens[1].length();
                          if (trainingMode)
                            depNodes.add( new ConllDependencyNode(jCas,wordStart,wordEnd) );
                          BaseToken btoken = new BaseToken(jCas,wordStart,wordEnd);
                          btoken.setTokenNumber(wordNumber++);
                          btoken.setNormalizedForm(tokens[2]);
                          btoken.setPartOfSpeech(tokens[4]);
                          btoken.addToIndexes();
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
            while (sentences.hasNext()) {
                Sentence sentence = (Sentence) sentences.next();


                ConllDependencyNode node = null;
                FSIterator nodeIterator = nodeIndex.subiterator(sentence);
                while (nodeIterator.hasNext()) {
//                    int pID = (node==null)? 0 : node.getID();
                    node = (ConllDependencyNode) nodeIterator.next();
                   
                    if (node.getId()!=0 ) { // && node.getID() !=pID) {

                        if (iv_outputFormat.toLowerCase().contains("min")) {
                            bw.write(node.getId()+"\t");
                            bw.write(node.getForm()+"\t");
                            bw.write( (node.getHead()==null ? "_" : node.getHead().getId()) + "\t");
                            bw.write(node.getDeprel()+"\n");
                        } else if (iv_outputFormat.toLowerCase().contains("mpos")) {
                            bw.write(node.getId()+"\t");
                            bw.write(node.getForm()+"\t");
                            bw.write(node.getPostag()+"\t");
                            bw.write( (node.getHead()==null ? "_" : node.getHead().getId()) + "\t");
                            bw.write(node.getDeprel()+"\n");
                        } else if (iv_outputFormat.toLowerCase().contains("mlem")) {
                            bw.write(node.getId()+"\t");
                            bw.write(node.getForm()+"\t");
                            bw.write(node.getLemma()+"\t");
                            bw.write( (node.getHead()==null ? "_" : node.getHead().getId()) + "\t");
                            bw.write(node.getDeprel()+"\n");
                        } else if (iv_outputFormat.toLowerCase().contains("dep")) {
                            bw.write(node.getId()+"\t");
                            bw.write(node.getForm()+"\t");
                            bw.write(node.getLemma()+"\t");
                            bw.write(node.getPostag()+"\t");
                            bw.write( (node.getHead()==null ? "_" : node.getHead().getId()) + "\t");
                            bw.write(node.getDeprel()+"\n");
                        } else { //if (iv_outputFormat.toLowerCase().contains("conll")) {
                            bw.write(node.getId()+"\t");
                            bw.write(node.getForm()+"\t");
                            bw.write(node.getLemma()+"\t");
                            bw.write(node.getCpostag()+"\t");
                            bw.write(node.getPostag()+"\t");
                            bw.write(node.getFeats()+"\t");
                            bw.write( (node.getHead()==null ? "_" : node.getHead().getId()) + "\t");
                            bw.write(node.getDeprel()+"\t");
                            bw.write( (node.getPhead()==null ? "_" : node.getPhead().getId()) + "\t");
                            bw.write(node.getPdeprel()+"\n");
                        }
                    }
                   
                }
                bw.write("\n");
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
  public static ConllDependencyNode getDependencyNode(JCas jCas, Annotation annot) {

    AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
      FSIterator nodeIterator = nodeIndex.iterator();
      while (nodeIterator.hasNext()) {
          ConllDependencyNode node = (ConllDependencyNode) nodeIterator.next();
          if (equalCoverage(annot,node)) {
            return node;
          }
      }
      return null;
View Full Code Here
97
98
99
100
101
102
103
104
105
106
107
  public static List<ConllDependencyNode> getDependencyNodes(JCas jCas, Annotation annot) {
    ArrayList<ConllDependencyNode> output = new ArrayList<ConllDependencyNode>();
    AnnotationIndex nodeIndex = jCas.getAnnotationIndex(ConllDependencyNode.type);
      FSIterator nodeIterator = nodeIndex.iterator();
      while (nodeIterator.hasNext()) {
          ConllDependencyNode node = (ConllDependencyNode) nodeIterator.next();
          if (doesSubsume(annot,node)) {
            output.add(node);
          }
      }
      return output;
View Full Code Here
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
    pathLtoR.clear();
    boolean foundMatch = false;
    for (int i=0; i<pathUp1.size(); i++ ) {
     
      // Assemble the part of the path from node1 to common ancestor
      ConllDependencyNode nodeUp1 = pathUp1.get(i);
      pathLtoR.add(nodeUp1);

      // Check each node above node2 for a match
      pathRtoL.clear();
      for (int j=0; j<pathUp2.size(); j++ ) {
        ConllDependencyNode nodeUp2 = pathUp2.get(j);       
        if (DependencyUtility.equalCoverage(nodeUp1, nodeUp2)) {
          // word-rel<word-rel<commonparent>rel-word>rel-word
          pathLtoR.setCommonNode(nodeUp1);
         
          // add the two halves of the path together
View Full Code Here
299
300
301
302
303
304
305
306
307
308
309
    return pathUp1;
  }

  public static List<ConllDependencyNode> getRightSibs( ConllDependencyNode refNode, List<ConllDependencyNode> tree ) {
   
    ConllDependencyNode parent = refNode.getHead();
    List<ConllDependencyNode> out = new ArrayList<ConllDependencyNode>();
   
    for ( ConllDependencyNode node : tree.subList( tree.indexOf(refNode)+1, tree.size() ) ) {
      if ( node.getHead().equals(parent) ) {
        out.add(node);
View Full Code Here
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
    return out;
  }
 
  public static List<ConllDependencyNode> getLeftSibs( ConllDependencyNode refNode, List<ConllDependencyNode> tree ) {
   
    ConllDependencyNode parent = refNode.getHead();
    List<ConllDependencyNode> out = new ArrayList<ConllDependencyNode>();
   
    List<ConllDependencyNode> lSide = tree.subList(0,tree.indexOf(refNode));
    for ( int i=tree.indexOf(refNode)-1; i>=0; i-- ) {
      ConllDependencyNode node = lSide.get(i);
      if ( node.getHead().equals(parent) ) {
        out.add(node);
      }
    }
    return out;
  }
View Full Code Here
338
339
340
341
342
343
344
345
346
347
348
349
350
351
      if ( node.equals(refNode) ) {
        out.add(node);
      } else {
       
        // Anything with refNode on its path to root is progeny.  Requires acyclicity
        ConllDependencyNode upNode = node;
        while (upNode.getHead()!=null) {
          upNode = upNode.getHead();
          if (upNode.equals(refNode)) {
            out.add(node);
            break;
          }
        }
       
View Full Code Here
367
368
369
370
371
372
373
374
375
376
377
378
379
      if ( refNodes.contains(node) ) {
        out.add(node);
      } else {
       
        // Anything with refNode on its path to root is progeny.  Requires acyclicity
        ConllDependencyNode upNode = node;
        while (upNode.getHead()!=null) {
          upNode = upNode.getHead();
         
          if (refNodes.contains(upNode)) {
            out.add(node);
            break;
          }
View Full Code Here
396
397
398
399
400
401
402
403
404
405
406

  public static String dumpDependencyGraph(Annotation annotation) {
    StringBuilder builder = new StringBuilder();
    for (ConllDependencyNode depNode : JCasUtil.selectCovered(ConllDependencyNode.class, annotation)) {
      ConllDependencyNode head = depNode.getHead();
      String headStr = (head != null) ? head.getCoveredText() : "TOP";
      builder.append(String.format("%s(%s, %s)\n", depNode.getDeprel(), depNode.getCoveredText(), headStr));
    }
    return builder.toString();
  }
View Full Code Here
TOP

Related Classes of org.apache.ctakes.typesystem.type.syntax.ConllDependencyNode

  • org.apache.ctakes.assertion.attributes.features.GenericFeaturesExtractor
  • org.apache.ctakes.assertion.attributes.features.HistoryFeaturesExtractor
  • org.apache.ctakes.assertion.attributes.features.SubjectFeaturesExtractor
  • org.apache.ctakes.assertion.attributes.generic.GenericAttributeClassifier
  • org.apache.ctakes.assertion.attributes.history.HistoryAttributeClassifier
  • org.apache.ctakes.assertion.attributes.subject.SubjectAttributeClassifier
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.NegationDependencyFeatureExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.SRLFeatureExtractor
  • org.apache.ctakes.assertion.util.AssertionDepUtils
  • org.apache.ctakes.assertion.util.NegationManualDepContextAnalyzer
    • 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.