Package org.apache.ctakes.dictionary.lookup2.dictionary.RareWordTermMapCreator

Examples of org.apache.ctakes.dictionary.lookup2.dictionary.RareWordTermMapCreator.CuiTuiTerm

39
40
41
42
43
44
45
46
47
48
49
   final private TextSpan _textSpan;
   final private String _text;
   private String _variant;

   public FastLookupToken( final Annotation jcasAnnotation ) {
      _textSpan = new DefaultTextSpan( jcasAnnotation.getBegin(), jcasAnnotation.getEnd() );
      _text = jcasAnnotation.getCoveredText().toLowerCase();
      if ( jcasAnnotation instanceof WordToken ) {
         final String canonicalForm = ((WordToken)jcasAnnotation).getCanonicalForm();
         // If canonical is not null AND not the same as the plain text then it is a valid variant for lookup
         if ( canonicalForm != null && !canonicalForm.equals( _text ) ) {
View Full Code Here
187
188
189
190
191
192
193
194
195
196
      if ( missingSpanKeys.isEmpty() ) {
         return new SpannedRareWordTerm( rareWordHit,
                                         allTokens.get( firstWordIndex ).getStart(),
                                         allTokens.get( lastWordIndex ).getEnd() );
      }
      final TextSpan discontiguousSpanKey = new MultiTextSpan( allTokens.get( firstWordIndex ).getStart(),
                                                                     allTokens.get( lastWordIndex ).getEnd(),
                                                                     missingSpanKeys );
      return new SpannedRareWordTerm( rareWordHit, discontiguousSpanKey );
   }
View Full Code Here
187
188
189
190
191
192
193
194
195
196
      if ( missingSpanKeys.isEmpty() ) {
         return new SpannedRareWordTerm( rareWordHit,
                                         allTokens.get( firstWordIndex ).getStart(),
                                         allTokens.get( lastWordIndex ).getEnd() );
      }
      final TextSpan discontiguousSpanKey = new MultiTextSpan( allTokens.get( firstWordIndex ).getStart(),
                                                                     allTokens.get( lastWordIndex ).getEnd(),
                                                                     missingSpanKeys );
      return new SpannedRareWordTerm( rareWordHit, discontiguousSpanKey );
   }
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
         final Map<TextSpan, Collection<RareWordTerm>> lookupHitMap ) {
      final Collection<TextSpan> discardSpans = new HashSet<TextSpan>();
      final List<TextSpan> textSpans = new ArrayList<TextSpan>( lookupHitMap.keySet() );
      final int count = textSpans.size();
      for ( int i=0; i<count; i++ ) {
         final TextSpan spanKeyI = textSpans.get( i );
         for ( int j=i+1; j<count; j++ ) {
            final TextSpan spanKeyJ = textSpans.get( j );
            if ( (spanKeyJ.getStart() <= spanKeyI.getStart() && spanKeyJ.getEnd() > spanKeyI.getEnd())
                  || (spanKeyJ.getStart() < spanKeyI.getStart() && spanKeyJ.getEnd() >= spanKeyI.getEnd()) ) {
               // J contains I, discard less precise concepts for span I and move on to next span I
               if ( spanKeyJ instanceof MultiTextSpan ) {
                  boolean spanIok = false;
                  for ( TextSpan missingSpanKey : ((MultiTextSpan)spanKeyJ).getMissingSpans() ) {
                     if ( (missingSpanKey.getStart() >= spanKeyI.getStart() && missingSpanKey.getStart() < spanKeyI.getEnd())
                           || (missingSpanKey.getEnd() > spanKeyI.getStart() && missingSpanKey.getEnd() <= spanKeyI.getEnd()) ) {
                        // I overlaps a missing span, so it is actually ok
                        spanIok = true;
                        break;
                     }
                  }
                  if ( !spanIok ) {
                     discardSpans.add( spanKeyI );
                     break;
                  }
               } else {
                  discardSpans.add( spanKeyI );
                  break;
               }
            }
            if ( ( (spanKeyI.getStart() <= spanKeyJ.getStart() && spanKeyI.getEnd() > spanKeyJ.getEnd() )
                  || (spanKeyI.getStart() < spanKeyJ.getStart() && spanKeyI.getEnd() >= spanKeyJ.getEnd()) ) ) {
               // I contains J, discard less precise concepts for span J and move on to next span J
               if ( spanKeyI instanceof MultiTextSpan ) {
                  boolean spanJok = false;
                  for ( TextSpan missingSpanKey : ((MultiTextSpan)spanKeyI).getMissingSpans() ) {
                     if ( (missingSpanKey.getStart() >= spanKeyJ.getStart() && missingSpanKey.getStart() < spanKeyJ.getEnd())
                           || (missingSpanKey.getEnd() > spanKeyJ.getStart() && missingSpanKey.getEnd() <= spanKeyJ.getEnd()) ) {
                        // J overlaps a missing span, so it is actually ok
                        spanJok = true;
                        break;
                     }
                  }
View Full Code Here
164
165
166
167
168
169
170
      }
      final Map<String, RareWordDictionary> dictionaries
            = parseDictionaries( uimaContext, doc.getRootElement().getChild( DICTIONARIES_KEY ) );
      final TermConsumer consumer = parseConsumerXml( uimaContext,
                                                              doc.getRootElement().getChild( CONSUMER_KEY ) );
      return new DictionarySpec( dictionaries.values(), consumer );
   }
View Full Code Here
251
252
253
254
255
256
257
258
259
            final String partOfSpeech = baseToken.getPartOfSpeech();
            if ( partOfSpeech == null || !_exclusionPartsOfSpeech.contains( partOfSpeech ) ) {
               lookupTokenIndices.add( allTokens.size() );
            }
         }
         final FastLookupToken lookupToken = new FastLookupToken( baseToken );
         allTokens.add( lookupToken );
      }
   }
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
   public void findTerms( final RareWordDictionary dictionary,
                           final List<FastLookupToken> allTokens, final List<Integer> lookupTokenIndices,
                           final Collection<SpannedRareWordTerm> termsFromDictionary ) {
      Collection<RareWordTerm> rareWordHits;
      for ( Integer lookupTokenIndex : lookupTokenIndices ) {
         final FastLookupToken lookupToken = allTokens.get( lookupTokenIndex );
         rareWordHits = dictionary.getRareWordHits( lookupToken );
         if ( rareWordHits == null || rareWordHits.isEmpty() ) {
            continue;
         }
         for ( RareWordTerm rareWordHit : rareWordHits ) {
            if ( rareWordHit.getTokenCount() == 1 ) {
               // Single word term, add and move on
               termsFromDictionary.add( new SpannedRareWordTerm( rareWordHit, lookupToken.getTextSpan() ) );
               continue;
            }
            final int termStartIndex = lookupTokenIndex - rareWordHit.getRareWordIndex();
            if ( termStartIndex < 0 || termStartIndex + rareWordHit.getTokenCount() > allTokens.size() ) {
               // term will extend beyond window
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
   public void findTerms( final RareWordDictionary dictionary,
                          final List<FastLookupToken> allTokens, final List<Integer> lookupTokenIndices,
                          final Collection<SpannedRareWordTerm> termsFromDictionary ) {
      Collection<RareWordTerm> rareWordHits;
      for ( Integer lookupTokenIndex : lookupTokenIndices ) {
         final FastLookupToken lookupToken = allTokens.get( lookupTokenIndex );
         rareWordHits = dictionary.getRareWordHits( lookupToken );
         if ( rareWordHits == null || rareWordHits.isEmpty() ) {
            continue;
         }
         for ( RareWordTerm rareWordHit : rareWordHits ) {
            if ( rareWordHit.getTokenCount() == 1 ) {
               // Single word term, add and move on
               termsFromDictionary.add( new SpannedRareWordTerm( rareWordHit, lookupToken.getTextSpan() ) );
               continue;
            }
            final int termStartIndex = lookupTokenIndex - rareWordHit.getRareWordIndex();
            if ( termStartIndex < 0 || termStartIndex + rareWordHit.getTokenCount() > allTokens.size() ) {
               // term will extend beyond window
View Full Code Here
TOP

Related Classes of org.apache.ctakes.dictionary.lookup2.dictionary.RareWordTermMapCreator.CuiTuiTerm

  • org.apache.ctakes.core.resource.FileResource
  • org.apache.ctakes.dictionary.lookup2.ae.AbstractJCasTermAnnotator
  • org.apache.ctakes.dictionary.lookup2.ae.DefaultJCasTermAnnotator
  • org.apache.ctakes.dictionary.lookup2.ae.OverlapJCasTermAnnotator
  • org.apache.ctakes.dictionary.lookup2.consumer.PrecisionTermConsumer
  • org.apache.ctakes.dictionary.lookup2.consumer.TermConsumer
  • org.apache.ctakes.dictionary.lookup2.consumer.WsdTermConsumer.RelatedCui
  • org.apache.ctakes.dictionary.lookup2.dictionary.BsvRareWordDictionary
  • org.apache.ctakes.dictionary.lookup2.dictionary.DictionaryDescriptorParser
  • org.apache.ctakes.dictionary.lookup2.dictionary.JdbcRareWordDictionary
    • 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.