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

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

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
    public static final void setup() throws IOException {
        ci = ciFactory.createContentItem(new StringSource(text));
        textBlob = ContentItemHelper.getBlob(ci, Collections.singleton("text/plain"));
        analysedTextWithData = createAnalysedText();
        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));
View Full Code Here
152
153
154
155
156
157
158
159
160
161
162
163
164
        //first the sentences
        TokenStream sentences = new SentenceTokenizer(new CharSequenceReader(at.getText()));
        try {
            while(sentences.incrementToken()){
                OffsetAttribute offset = sentences.addAttribute(OffsetAttribute.class);
                Sentence s = at.addSentence(offset.startOffset(), offset.endOffset());
                if(log.isTraceEnabled()) {
                    log.trace("detected {}:{}",s,s.getSpan());
                }
            }
        } catch (IOException e) {
            String message = String.format("IOException while reading from "
                +"CharSequenceReader of AnalyzedText for ContentItem %s",ci.getUri());
View Full Code Here
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
306
307
308
309
310
311
312
313
314
315
316
317
            } else {
                throw RuntimeException.class.cast(e);
            }
        }
        Iterator<Span> spans = at.getEnclosed(EnumSet.of(SpanTypeEnum.Sentence,SpanTypeEnum.Chunk));
        Sentence context = null;
        MGraph metadata = ci.getMetadata();
        Language lang = new Language(language);
        LiteralFactory lf = LiteralFactory.getInstance();
        ci.getLock().writeLock().lock();
        try { //write TextAnnotations for Named Entities
            while(spans.hasNext()){
                Span span = spans.next();
                switch (span.getType()) {
                    case Sentence:
                        context = (Sentence)context;
                        break;
                    default:
                        Value<NerTag> nerAnno = span.getAnnotation(NER_ANNOTATION);
                        if(nerAnno != null){
                            UriRef ta = EnhancementEngineHelper.createTextEnhancement(ci, this);
                            //add span related data
                            metadata.add(new TripleImpl(ta, ENHANCER_SELECTED_TEXT,
                                new PlainLiteralImpl(span.getSpan(), lang)));
                            metadata.add(new TripleImpl(ta, ENHANCER_START,
                                lf.createTypedLiteral(span.getStart())));
                            metadata.add(new TripleImpl(ta, ENHANCER_END,
                                lf.createTypedLiteral(span.getEnd())));
                            metadata.add(new TripleImpl(ta, ENHANCER_SELECTION_CONTEXT,
                                new PlainLiteralImpl(context == null ?
                                        getDefaultSelectionContext(at.getSpan(), span.getSpan(), span.getStart()) :
                                            context.getSpan(), lang)));
                            //add the NER type
                            if(nerAnno.value().getType() != null){
                                metadata.add(new TripleImpl(ta,DC_TYPE,nerAnno.value().getType()));
                            }
                            if(nerAnno.probability() >= 0) {
View Full Code Here
174
175
176
177
178
179
180
181
182
183
184
        String language = getLanguage(this, ci, true);
        SentenceDetector sentenceDetector = getSentenceDetector(language);
        if(sentenceDetector != null){
            for(opennlp.tools.util.Span sentSpan : sentenceDetector.sentPosDetect(at.getSpan())) {
                //detect sentences and add it to the AnalyzedText.
                Sentence sentence = at.addSentence(sentSpan.getStart(), sentSpan.getEnd());
                log.trace(" > add {}",sentence);
            }
        } else {
            log.warn("SentenceDetector model for language {} is no longer available. "
                + "This might happen if the model becomes unavailable during enhancement. "
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
            //first the sentences
            TokenStream sentences = new SentenceTokenizer(new CharSequenceReader(at.getText()));
            try {
                while(sentences.incrementToken()){
                    OffsetAttribute offset = sentences.addAttribute(OffsetAttribute.class);
                    Sentence s = at.addSentence(offset.startOffset(), offset.endOffset());
                    if(log.isTraceEnabled()) {
                        log.trace("detected {}:{}",s,s.getSpan());
                    }
                }
            } catch (IOException e) {
                String message = String.format("IOException while reading from "
                    +"CharSequenceReader of AnalyzedText for ContentItem %s",ci.getUri());
View Full Code Here
371
372
373
374
375
376
377
378
379
380
381
        SentenceDetector sentenceDetector = getSentenceDetector(language);
        List<Section> sentences;
        if(sentenceDetector != null){
            sentences = new ArrayList<Section>();
            for(opennlp.tools.util.Span sentSpan : sentenceDetector.sentPosDetect(at.getSpan())) {
                Sentence sentence = at.addSentence(sentSpan.getStart(), sentSpan.getEnd());
                log.trace(" > add {}",sentence);
                sentences.add(sentence);
            }
        } else {
            sentences = null;
View Full Code Here
TOP

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

  • org.apache.stanbol.enhancer.engines.kuromoji.impl.KuromojiNlpEngine
  • org.apache.stanbol.enhancer.engines.opennlp.pos.services.OpenNlpPosTaggingEngine
  • org.apache.stanbol.enhancer.engines.opennlp.sentence.impl.OpenNlpSentenceDetectionEngine
  • org.apache.stanbol.enhancer.engines.restful.nlp.impl.RestfulNlpAnalysisEngine
  • org.apache.stanbol.enhancer.engines.sentiment.summarize.SentimentSummarizationEngine
  • org.apache.stanbol.enhancer.engines.smartcn.impl.SmartcnSentenceEngine
  • org.apache.stanbol.enhancer.engines.smartcn.impl.SmartcnTokenizerEngine
  • org.apache.stanbol.enhancer.nlp.json.AnalyzedTextSerializerAndParserTest
  • org.apache.stanbol.enhancer.nlp.json.valuetype.CorefFeatureSupportTest
  • org.apache.stanbol.enhancer.nlp.json.valuetype.DependencyRelationSupportTest
    • 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.