Package org.cleartk.classifier

Examples of org.cleartk.classifier.Feature

69
70
71
72
73
74
75
76
77
78
  private Collection<? extends Feature> hashToFeatureList(
      HashMap<String, Boolean> featsIn) {
   
    Collection<Feature> featsOut = new HashSet<Feature>();
    for (String featName : featsIn.keySet()) {
      featsOut.add(new Feature(featName,featsIn.get(featName)));
    }
   
    return featsOut;
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
    List<Feature> features = new ArrayList<Feature>();
   
    // Pull in general dependency-based features -- externalize to another extractor?
      ConllDependencyNode node = DependencyUtility.getNominalHeadNode(jCas, arg);
      if (node!= null) {
        features.add(new Feature("DEPENDENCY_HEAD", node.getCoveredText()));
        features.add(new Feature("DEPENDENCY_HEAD_deprel", node.getDeprel()));
    }
     
      HashMap<String, Boolean> featsMap = SubjectAttributeClassifier.extract(jCas, arg);

      if (!featsMap.isEmpty()) {
        // Pull in all the features that were used for the rule-based module
        features.addAll( hashToFeatureList(featsMap) );
        // Pull in the result of the rule-based module as well
        features.add(new Feature("SUBJECT_CLASSIFIER_LOGIC", SubjectAttributeClassifier.classifyWithLogic(featsMap)));
      }
     
      return features;
  }
View Full Code Here
70
71
72
73
74
75
76
77
78
79
  private Collection<? extends Feature> hashToFeatureList(
      HashMap<String, Boolean> featsIn) {
   
    Collection<Feature> featsOut = new HashSet<Feature>();
    for (String featName : featsIn.keySet()) {
      featsOut.add(new Feature(featName,featsIn.get(featName)));
    }
   
    return featsOut;
  }
View Full Code Here
36
37
38
39
40
41
42
43
      tree = TreeExtractor.getSimpleClone(t2);
    }else{
      tree = TreeExtractor.extractPathEnclosedTree(t1, t2, jcas);
    }

    features.add(new Feature("TK_PET", tree.toString()));
    return features;
  }
View Full Code Here
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
    List<Feature> features = new ArrayList<Feature>();
   
    // entity1 ... entity2 scenario
    if(arg1.getEnd() < arg2.getBegin()) {
      features.add(new Feature("arg1_arg2", true));
    }
   
    // entity2 ... entity1 scenario
    if(arg2.getEnd() < arg1.getBegin()) {
      features.add(new Feature("arg2_arg1", true));
    }
   
    return features;
  }
View Full Code Here
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
       
    // Extract features between
    List<TerminalTreebankNode> headList = this.extractPhraseHeadByTreenode(jCas, JCasUtil.selectCovered(jCas, TreebankNode.class, arg1.getEnd(), arg2.getBegin()));

    if(headList.size() > 0) {
      features.add(new Feature("PhraseChunk_Between_FirstHead", headList.get(0).getNodeValue()));
      features.add(new Feature("PhraseChunk_Between_LastHead", headList.get(headList.size()-1).getNodeValue()));
     
      if(headList.size() >= 2) {
        String inBetweenValue = "";
        for(int i=1;i<headList.size()-1;i++) {
          if(i>1)
            inBetweenValue += "_";
          inBetweenValue += headList.get(i).getNodeValue();
        }
        features.add(new Feature("PhraseChunk_Between_BetweenHeads", inBetweenValue));
      }
    }
   
    // Extract feature before M1
    headList = this.extractPhraseHeadByTreenode(jCas, JCasUtil.selectPreceding(jCas, TreebankNode.class, arg1, 20));

    boolean isFirst = false;
    for(int i=headList.size()-1;i>=0;i--) {
      if(headList.get(i).getEnd() < arg1.getBegin()) {
        if(!isFirst) {
        features.add(new Feature("PhraseChunk_Before_FirstHead", headList.get(i).getNodeValue()));
        isFirst = true;
        }
        else {
          features.add(new Feature("PhraseChunk_Before_SecondHead", headList.get(i).getNodeValue()));
          break;
        }
      }
    }
   
    // Extract feature after M2
    headList = this.extractPhraseHeadByTreenode(jCas, JCasUtil.selectFollowing(jCas, TreebankNode.class, arg2, 20));
   
   
    isFirst = false;
    for(int i=0;i<headList.size();i++) {
      if(headList.get(i).getBegin() > arg2.getEnd() ) {
        if(!isFirst) {
          features.add(new Feature("PhraseChunk_After_FirstHead", headList.get(i).getNodeValue()));
          isFirst = true;
        }
        else {
          features.add(new Feature("PhraseChunk_After_SecondHead", headList.get(i).getNodeValue()));
          break;
        }
      }
    }
   
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
    features.addAll(this.nEntityMentionsBetween.extract(jCas, arg1, arg2));

    // entity type of both mentions, concatenated
    int type1 = arg1.getTypeID();
    int type2 = arg2.getTypeID();
    features.add(new Feature("type1type2", String.format("%s_%s", type1, type2)));

    // is mention1 included in mention2?
    boolean begins1After2 = arg1.getBegin() >= arg2.getBegin();
    boolean ends1Before2 = arg1.getEnd() <= arg2.getEnd();
    features.add(new Feature("mention1InMention2", begins1After2 && ends1Before2));

    // is mention2 included in mention1?
    boolean begins2After1 = arg2.getBegin() >= arg1.getBegin();
    boolean ends2Before1 = arg2.getEnd() <= arg1.getEnd();
    features.add(new Feature("mention2InMention1", begins2After1 && ends2Before1));

    return features;
  }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
      tree = TreeExtractor.extractPathEnclosedTree(t1, t2, jcas);
    }

    for(SimpleTree frag : frags){
      if(TreeUtils.containsIgnoreCase(tree, frag)){
        features.add(new Feature("TK_" + frag.toString()));
        //      }else{
        //        features.add(new Feature(frag.toString(), false));
      }
    }
View Full Code Here
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
            closest = tokens.size();
          }
//          instance.addAll(cuePhraseInWindowExtractor.extractBetween(jCas, cue, entityOrEventMention));
        }
        if(closestCue != null && closest < 21){
          instance.add(new Feature("ClosestCue_Word", closestCue.getCoveredText()));
//          instance.add(new Feature("ClosestCue_Phrase", closestCue.getCuePhrase()));
          instance.add(new Feature("ClosestCue_PhraseFamily", closestCue.getCuePhraseAssertionFamily()));
          instance.add(new Feature("ClosestCue_PhraseCategory", closestCue.getCuePhraseCategory()));
        }
      }
//      if (cuePhraseFeatures != null && !cuePhraseFeatures.isEmpty())
//      {
//        instance.addAll(cuePhraseFeatures);
//      }


      // 7/9/13 SRH trying to make it work just for anatomical site
      int eemTypeId = entityOrEventMention.getTypeID();
      if (eemTypeId == CONST.NE_TYPE_ID_ANATOMICAL_SITE) {
          // 7/9/13 srh modified per tmiller so it's binary but not numeric feature
          //instance.add(new Feature("ENTITY_TYPE_" + entityOrEventMention.getTypeID()));
          instance.add(new Feature("ENTITY_TYPE_ANAT_SITE"));
      } /* This hurts recall more than it helps precision
      else if (eemTypeId == CONST.NE_TYPE_ID_DRUG) {
        // 7/10 adding drug
        instance.add(new Feature("ENTITY_TYPE_DRUG"));
      }
View Full Code Here
425
426
427
428
429
430
431
432
433
434
435
436
437
    }
   
    ArrayList<Feature> featureList = new ArrayList<Feature>();
    for (Zone zone : zoneList)
    {
      Feature currentFeature = new Feature("zone", zone.getLabel());
      logger.debug(String.format("zone: %s", zone.getLabel()));
      logger.debug(String.format("zone feature: %s", currentFeature.toString()));
      featureList.add(currentFeature);
    }
   
    return featureList;
  }
View Full Code Here
TOP

Related Classes of org.cleartk.classifier.Feature

  • 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.medfacts.cleartk.AssertionCleartkAnalysisEngine
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.AboveLeftFragmentExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.AboveRightFragmentExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.BrownClusterFeatureFunction
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.ContextWordWindowExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.DependencyWordsFragmentExtractor
  • org.apache.ctakes.assertion.medfacts.cleartk.extractors.FedaFeatureFunction
    • 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.