Package org.apache.stanbol.enhancer.nlp.model

Examples of org.apache.stanbol.enhancer.nlp.model.Token

199
200
201
202
203
204
205
206
207
208
        while(sections.hasNext()){
            Section section = sections.next();
            //Tokenize section
            opennlp.tools.util.Span[] tokenSpans = tokenizer.tokenizePos(section.getSpan());
            for(int i=0;i<tokenSpans.length;i++){
                Token token = section.addToken(tokenSpans[i].getStart(), tokenSpans[i].getEnd());
                log.trace(" > add {}",token);
            }
        }
    }
View Full Code Here
222
223
224
225
226
227
228
229
230
231
232
            for(PhraseBuilder pb : phraseBuilders){
                pb.nextSection(sentence);
            }
            Iterator<Token> tokens = sentence.getTokens();
            while(tokens.hasNext()){
                Token token = tokens.next();
                for(PhraseBuilder pb : phraseBuilders){
                    pb.nextToken(token);
                }
            }
        }
View Full Code Here
146
147
148
149
150
151
152
153
154
155
156
        return states[0];
    }
   
    @SuppressWarnings("unchecked") //varargs with generic types
    private void buildPhrase(Token token) {
        Token lastConsumedToken = null;
        if(valid){
            //search backwards for the first token matching an allowed end
            //category
            int endIndex = current.size()-1;
            while(endIndex > 0 && !checkCategories(current.get(endIndex),
View Full Code Here
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
        OffsetAttribute offset = null;
        try {
          tokenStream.reset(); //required with Solr 4
            while (tokenStream.incrementToken()){
                offset = tokenStream.addAttribute(OffsetAttribute.class);
                Token token = at.addToken(offset.startOffset(), offset.endOffset());
                //Get the POS attribute and init the PosTag
                PartOfSpeechAttribute posAttr = tokenStream.addAttribute(PartOfSpeechAttribute.class);
                PosTag posTag = POS_TAG_SET.getTag(posAttr.getPartOfSpeech());
                if(posTag == null){
                    posTag = adhocTags.get(posAttr.getPartOfSpeech());
                    if(posTag == null){
                        posTag = new PosTag(posAttr.getPartOfSpeech());
                        adhocTags.put(posAttr.getPartOfSpeech(), posTag);
                        log.warn(" ... missing PosTag mapping for {}",posAttr.getPartOfSpeech());
                    }
                }
                //Sentence detection by POS tag
                if(sentStartOffset < 0){ //the last token was a sentence ending
                  sentStartOffset = offset.startOffset();
                }
                if(posTag.hasPos(Pos.Point)) {
                    Sentence sent = at.addSentence(sentStartOffset, offset.startOffset());
                    //add the sentence as context to the NerData instances
                    while(nerSentIndex < nerList.size()){
                        nerList.get(nerSentIndex).context = sent.getSpan();
                        nerSentIndex++;
                    }
                    sentStartOffset = -1;
                }
                //POS
                token.addAnnotation(POS_ANNOTATION, Value.value(posTag));
                //NER
                NerTag nerTag = NER_TAG_SET.getTag(posAttr.getPartOfSpeech());
                if(ner != null && (nerTag == null || !ner.tag.getType().equals(nerTag.getType()))){
                    //write NER annotation
                    Chunk chunk = at.addChunk(ner.start, ner.end);
                    chunk.addAnnotation(NlpAnnotations.NER_ANNOTATION, Value.value(ner.tag));
                    //NOTE that the fise:TextAnnotation are written later based on the nerList
                    //clean up
                    ner = null;
                }
                if(nerTag != null){
                    if(ner == null){
                        ner = new NerData(nerTag, offset.startOffset());
                        nerList.add(ner);
                    }
                    ner.end = offset.endOffset();
                }
                BaseFormAttribute baseFormAttr = tokenStream.addAttribute(BaseFormAttribute.class);
                MorphoFeatures morpho = null;
                if(baseFormAttr != null && baseFormAttr.getBaseForm() != null){
                  morpho = new MorphoFeatures(baseFormAttr.getBaseForm());
                  morpho.addPos(posTag); //and add the posTag
                }
                InflectionAttribute inflectionAttr = tokenStream.addAttribute(InflectionAttribute.class);
                inflectionAttr.getInflectionForm();
                inflectionAttr.getInflectionType();
                if(morpho != null){ //if present add the morpho
                  token.addAnnotation(MORPHO_ANNOTATION, Value.value(morpho));
                }
            }
            //we still need to write the last sentence
            Sentence lastSent = null;
            if(offset != null && sentStartOffset >= 0 && offset.endOffset() > sentStartOffset){
View Full Code Here
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
            while(sentences.hasNext()){
                // (1) get Tokens and POS information for the sentence
                Section sentence = sentences.next();
                Iterator<Token> tokens = sentence.getTokens();
                while(tokens.hasNext()){
                    Token token = tokens.next();
                    tokenList.add(token);
                    tokenTextList.add(token.getSpan());
                    Value<PosTag> posValue = token.getAnnotation(POS_ANNOTATION);
                    if(posValue == null){
                        throw new EngineException("Missing POS value for Token '"
                            + token.getSpan()+"' of ContentItem "+ci.getUri()
                            + "(Sentence: '"+sentence.getSpan()+"'). This may "
                            + "indicate that a POS tagging Engine is missing in "
                            + "the EnhancementChain or that the used POS tagging "
                            + "does not provide POS tags for each token!");
                    } else {
View Full Code Here
118
119
120
121
122
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
        int sentence = text.indexOf('.')+1;
        Sentence sent1 = analysedTextWithData.addSentence(0, sentence);
        expectedSentences.put(sent1, "The Stanbol enhancer can detect famous " +
            "cities such as Paris and people such as Bob Marley.");
       
        Token the = sent1.addToken(0, 3);
        expectedTokens.put(the, "The");
        the.addAnnotation(NlpAnnotations.POS_ANNOTATION, Value.value(
            new PosTag("PREP",Pos.Preposition), 0.85));
       
        Token stanbol = sent1.addToken(4,11);
        expectedTokens.put(stanbol, "Stanbol");
        stanbol.addAnnotation(NlpAnnotations.POS_ANNOTATION, Value.value(
            new PosTag("PN", Pos.ProperNoun),0.95));
        stanbol.addAnnotation(NlpAnnotations.SENTIMENT_ANNOTATION, Value.value(
            0.5));
       
        //use index to create Tokens
        int enhancerStart = sent1.getSpan().toString().indexOf("enhancer");
        Token enhancer = sent1.addToken(enhancerStart,enhancerStart+"enhancer".length());
        expectedTokens.put(enhancer, "enhancer");
        enhancer.addAnnotation(NlpAnnotations.POS_ANNOTATION, Value.value(
            new PosTag("PN", Pos.ProperNoun),0.95));
        enhancer.addAnnotation(NlpAnnotations.POS_ANNOTATION, Value.value(
            new PosTag("N", LexicalCategory.Noun),0.87));
        MorphoFeatures morpho = new MorphoFeatures("enhance");
        morpho.addCase(new CaseTag("test-case-1",Case.Comitative));
        morpho.addCase(new CaseTag("test-case-2",Case.Abessive));
        morpho.addDefinitness(Definitness.Definite);
        morpho.addPerson(Person.First);
        morpho.addPos(new PosTag("PN", Pos.ProperNoun));
        morpho.addGender(new GenderTag("test-gender", Gender.Masculine));
        morpho.addNumber(new NumberTag("test-number", NumberFeature.Plural));
        morpho.addTense(new TenseTag("test-tense", Tense.Present));
        morpho.addVerbForm(new VerbMoodTag("test-verb-mood", VerbMood.ConditionalVerb));
        enhancer.addAnnotation(NlpAnnotations.MORPHO_ANNOTATION, Value.value(morpho));

        //create a chunk
        Chunk stanbolEnhancer = analysedTextWithData.addChunk(stanbol.getStart(), enhancer.getEnd());
        expectedChunks.put(stanbolEnhancer, "Stanbol enhancer");
        stanbolEnhancer.addAnnotation(NlpAnnotations.NER_ANNOTATION, Value.value(
            new NerTag("organization", DBPEDIA_ORGANISATION)));
        stanbolEnhancer.addAnnotation(NlpAnnotations.PHRASE_ANNOTATION, Value.value(
            new PhraseTag("NP", LexicalCategory.Noun),0.98));
View Full Code Here
110
111
112
113
114
115
116
117
118
119
120
121
122
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
        ci.getMetadata().add(new TripleImpl(ci.getUri(), DC_LANGUAGE, new PlainLiteralImpl("de")));
        Assert.assertEquals("de", EnhancementEngineHelper.getLanguage(ci));
       
        //Add some Tokens with POS annotations to test the usage of
        //existing POS annotations by the lemmatizer
        Token verbrachten = at.addToken(de_verbStart,de_verbStart+de_verb.length());
        verbrachten.addAnnotation(POS_ANNOTATION, Value.value(
            new PosTag("V",LexicalCategory.Verb), de_verbProb));
       
        Token schonen = at.addToken(de_adjectiveStart,de_adjectiveStart+de_adjective.length());
        schonen.addAnnotation(POS_ANNOTATION, Value.value(
            new PosTag("ADJ",LexicalCategory.Adjective), de_adjectiveProb));
       
        Token urlaub = at.addToken(de_nounStart,de_nounStart+de_noun.length());
        urlaub.addAnnotation(POS_ANNOTATION, Value.value(
            new PosTag("NC",LexicalCategory.Noun), de_nounProb));
       
        Assert.assertEquals("Can not enhance Test ContentItem",
            EnhancementEngine.ENHANCE_ASYNC,engine.canEnhance(ci));
        //compute the enhancements
        try {
            engine.computeEnhancements(ci);
        } catch (EngineException e) {
            RemoteServiceHelper.checkServiceUnavailable(e);
            return; //deactivate test
        }
        //now validate the enhancements
        boolean foundVerb = false;
        boolean foundAdjective = false;
        boolean foundNoun = false;
        for(Iterator<Token> tokens = at.getTokens(); tokens.hasNext();){
            Token token = tokens.next();
            log.info("Token: {}",token);
            List<Value<MorphoFeatures>> mfs = token.getAnnotations(NlpAnnotations.MORPHO_ANNOTATION);
            if(de_verb.equals(token.getSpan())){
                foundVerb = !mfs.isEmpty();
                validateMorphFeatureProbability(mfs,LexicalCategory.Verb,de_verbProb);
            } else if(de_adjective.equals(token.getSpan())){
                foundAdjective = !mfs.isEmpty();
                validateMorphFeatureProbability(mfs,LexicalCategory.Adjective,de_adjectiveProb);
            } else if(de_noun.equals(token.getSpan())){
                foundNoun = !mfs.isEmpty();
                validateMorphFeatureProbability(mfs,LexicalCategory.Noun,de_nounProb);
            }
            for(Value<MorphoFeatures> mf : mfs){
                log.info("  - {}",mf);
View Full Code Here
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
        //TODO: locking for AnalysedText not yet defined
//        ci.getLock().writeLock().lock();
//        try {
        Iterator<Token> tokens = analysedText.getTokens();
        while(tokens.hasNext()){
            Token token = tokens.next();
            boolean process = !adjectivesOnly;
            if(!process){ //check POS types
                Iterator<Value<PosTag>> posTags = token.getAnnotations(NlpAnnotations.POS_ANNOTATION).iterator();
                boolean ignore = false;
                while(!ignore && !process && posTags.hasNext()) {
                    Value<PosTag> value = posTags.next();
                    PosTag tag = value.value();
                    boolean state = classifier.isAdjective(tag) || classifier.isNoun(tag);
                    ignore = !state && value.probability() >= minPOSConfidence;
                    process = state && value.probability() >= (minPOSConfidence/2.0);
                }
            } //else process all tokens ... no POS tag checking needed
            if(process){
                double sentiment = classifier.classifyWord(token.getSpan());
                if(sentiment != 0.0){
                    token.addAnnotation(SENTIMENT_ANNOTATION, new Value<Double>(sentiment));
                } //else do not set sentiments with 0.0
            }
        }
//        } finally {
//            ci.getLock().writeLock().unlock();
View Full Code Here
476
477
478
479
480
481
482
483
484
485
486
487
488
            // get the tokens, words of the current sentence
            List<Token> tokens = new ArrayList<Token>(32);
            List<String> words = new ArrayList<String>(32);
            for(Iterator<Token> it =sentences.get(i).getTokens();it.hasNext();){
                Token t = it.next();
                tokens.add(t);
                words.add(t.getSpan());
            }
            Span[] nameSpans = finder.find(words.toArray(new String[words.size()]));
            double[] probs = finder.probs();
            //int lastStartPosition = 0;
            for (int j = 0; j < nameSpans.length; j++) {
View Full Code Here
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
            while(sentences.hasNext()){
                // (1) get Tokens and POS information for the sentence
                Section sentence = sentences.next();
                Iterator<Token> tokens = sentence.getTokens();
                while(tokens.hasNext()){
                    Token token = tokens.next();
                    tokenList.add(token);
                    tokenTextList.add(token.getSpan());
                    Value<PosTag> posValue = token.getAnnotation(POS_ANNOTATION);
                    if(posValue == null){
                        throw new EngineException("Missing POS value for Token '"
                            + token.getSpan()+" of ContentItem "+ci.getUri()
                            + "(Sentence: '"+sentence.getSpan()+"'). This may "
                            + "indicate that a POS tagging Engine is missing in "
                            + "the EnhancementChain or that the used POS tagging "
                            + "does not provide POS tags for each token!");
                    } else {
View Full Code Here
TOP

Related Classes of org.apache.stanbol.enhancer.nlp.model.Token

  • org.apache.stanbol.enhancer.engines.celi.lemmatizer.impl.CeliAnalyzedTextLemmatizerEngine
  • org.apache.stanbol.enhancer.engines.celi.lemmatizer.impl.CeliAnalyzedTextLemmatizerEngineTest
  • org.apache.stanbol.enhancer.engines.celi.sentimentanalysis.impl.CeliAnalyzedTextSentimentAnalysisEngine
  • org.apache.stanbol.enhancer.engines.celi.sentimentanalysis.impl.CeliAnalyzedTextSentimentAnalysisEngineTest
  • org.apache.stanbol.enhancer.engines.kuromoji.impl.KuromojiNlpEngine
  • org.apache.stanbol.enhancer.engines.opennlp.chunker.services.OpenNlpChunkingEngine
  • org.apache.stanbol.enhancer.engines.opennlp.impl.NEREngineCore
  • org.apache.stanbol.enhancer.engines.opennlp.pos.services.OpenNlpPosTaggingEngine
  • org.apache.stanbol.enhancer.engines.opennlp.token.impl.OpenNlpTokenizerEngine
  • org.apache.stanbol.enhancer.engines.poschunker.engine.PosChunkerEngine
    • 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.