public static AnalysisEngineDescription getPreprocessingDescription() throws ResourceInitializationException, MalformedURLException { AggregateBuilder builder = new AggregateBuilder(); builder.add(SimpleSegmentAnnotator.createAnnotatorDescription()); builder.add(SentenceDetector.createAnnotatorDescription()); builder.add(TokenizerAnnotatorPTB.createAnnotatorDescription()); // builder.add(LvgAnnotator.createAnnotatorDescription()); builder.add(ContextDependentTokenizerAnnotator.createAnnotatorDescription()); builder.add(POSTagger.createAnnotatorDescription()); builder.add(ClearNLPDependencyParserAE.createAnnotatorDescription()); builder.add(ConstituencyParser.createAnnotatorDescription()); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getTokenProcessingPipeline() throws ResourceInitializationException, MalformedURLException { AggregateBuilder builder = new AggregateBuilder(); builder.add( SimpleSegmentAnnotator.createAnnotatorDescription() ); builder.add( SentenceDetector.createAnnotatorDescription() ); builder.add( TokenizerAnnotatorPTB.createAnnotatorDescription() ); builder.add( LvgAnnotator.createAnnotatorDescription() ); builder.add( ContextDependentTokenizerAnnotator.createAnnotatorDescription() ); builder.add( POSTagger.createAnnotatorDescription() ); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getTokenProcessingPipeline() throws ResourceInitializationException, MalformedURLException { AggregateBuilder builder = new AggregateBuilder(); builder.add( SimpleSegmentAnnotator.createAnnotatorDescription() ); builder.add( SentenceDetector.createAnnotatorDescription() ); builder.add( TokenizerAnnotatorPTB.createAnnotatorDescription() ); builder.add( LvgAnnotator.createAnnotatorDescription() ); builder.add( ContextDependentTokenizerAnnotator.createAnnotatorDescription() ); builder.add( POSTagger.createAnnotatorDescription() ); return builder.createAggregateDescription(); }
/** * Builds the tokenizedInf preprocessing for ClearNLP * @return * @throws InvalidXMLException * @throws IOException */ public static AggregateBuilder getTokenizedInfPosAggregateBuilder() throws InvalidXMLException, IOException { AggregateBuilder aggregateBuilder = new AggregateBuilder(); aggregateBuilder.add(loadDescription(SIMPLE_SEGMENTER_PATH)); aggregateBuilder.add(loadDescription(LVG_BASE_TOKEN_ANNOTATOR_PATH)); aggregateBuilder.add(loadDescription(POS_TAGGER_PATH)); return aggregateBuilder; }
private static void writeAggregateDescriptions( AggregateBuilder preprocessing, AnalysisEngineDescription ClearNLPDepParserDesc, AnalysisEngineDescription ClearNLPSRLDesc, File outputRoot, String aggregateSuffix) throws ResourceInitializationException, FileNotFoundException, SAXException, IOException { // Append Dependency Parser into aggregate and write description file preprocessing.add(ClearNLPDepParserDesc); preprocessing.createAggregateDescription().toXML(new FileOutputStream(new File(outputRoot, DEP_NAME + aggregateSuffix))); // Append SRL Parser into aggregate and write description file preprocessing.add(ClearNLPSRLDesc); preprocessing.createAggregateDescription().toXML(new FileOutputStream(new File(outputRoot, SRL_NAME + aggregateSuffix))); }
public static AnalysisEngineDescription getNpChunkerPipeline() throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); builder.add( Chunker.createAnnotatorDescription() ); builder.add( getStandardChunkAdjusterAnnotator() ); builder.add( AnalysisEngineFactory.createEngineDescription( CopyNPChunksToLookupWindowAnnotations.class ) ); builder.add( AnalysisEngineFactory.createEngineDescription( RemoveEnclosedLookupWindows.class ) ); return builder.createAggregateDescription(); }
/** * Builds the tokenized preprocessing pipeline for ClearNLP * @return * @throws InvalidXMLException * @throws IOException */ public static AggregateBuilder getTokenizedAggregateBuilder() throws InvalidXMLException, IOException { AggregateBuilder aggregateBuilder = new AggregateBuilder(); aggregateBuilder.add(loadDescription(SIMPLE_SEGMENTER_PATH)); aggregateBuilder.add(loadDescription(LVG_BASE_TOKEN_ANNOTATOR_PATH)); return aggregateBuilder; }
public static AnalysisEngineDescription getLegacyCoreferencePipeline() throws ResourceInitializationException{ AggregateBuilder builder = new AggregateBuilder(); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkableCreator.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkableExpander.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkablePairGenerator.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqSvmChainCreator.class)); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getLegacyCoreferencePipeline() throws ResourceInitializationException{ AggregateBuilder builder = new AggregateBuilder(); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkableCreator.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkableExpander.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqMarkablePairGenerator.class)); builder.add(AnalysisEngineFactory.createEngineDescription(MipacqSvmChainCreator.class)); return builder.createAggregateDescription(); }
@Override public AnalysisEngineDescription createPreprocessingComponents(String language) throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); builder.add(getTokenizer(language)); builder.add(getTagger(language)); builder.add(getChunker(language)); builder.add(getCandidateAnnotator()); return builder.createAggregateDescription(); }
@Override public AnalysisEngineDescription createPreprocessingComponents(String language) throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); builder.add(getTokenizer(language)); builder.add(getTagger(language)); builder.add(getNamedEntityAnnotator()); builder.add(getCandidateAnnotator()); return builder.createAggregateDescription(); }
/** * Builds the tokenized preprocessing pipeline for ClearNLP * @return * @throws InvalidXMLException * @throws IOException */ public static AggregateBuilder getTokenizedAggregateBuilder() throws InvalidXMLException, IOException { AggregateBuilder aggregateBuilder = new AggregateBuilder(); aggregateBuilder.add(loadDescription(SIMPLE_SEGMENTER_PATH)); aggregateBuilder.add(loadDescription(LVG_BASE_TOKEN_ANNOTATOR_PATH)); return aggregateBuilder; }
public static AnalysisEngineDescription getParsingPipeline() throws ResourceInitializationException, MalformedURLException { AggregateBuilder builder = new AggregateBuilder(); builder.add( getTokenProcessingPipeline() ); builder.add( ClearNLPDependencyParserAE.createAnnotatorDescription() ); builder.add( AnalysisEngineFactory.createEngineDescription( ConstituencyParser.class ) ); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getCoreferencePipeline() throws ResourceInitializationException, MalformedURLException { AggregateBuilder builder = new AggregateBuilder(); builder.add(getFastPipeline()); builder.add(ConstituencyParser.createAnnotatorDescription()); builder.add(CoreferenceAnnotatorFactory.getDefaultCoreferencePipeline()); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getMentionClusterResolverDescription() throws ResourceInitializationException{ AggregateBuilder builder = new AggregateBuilder(); // Creates a data structure that maps from markables to dependency head nodes that is used in multiple feature extractors builder.add(AnalysisEngineFactory.createEngineDescription(MarkableHeadTreeCreator.class)); // annotate every markable for "salience": how important is it to the discourse in context builder.add(MarkableSalienceAnnotator.createAnnotatorDescription("/org/apache/ctakes/temporal/ae/salience/model.jar")); // use the mention-cluster model with default trained model: builder.add(MentionClusterCoreferenceAnnotator.createAnnotatorDescription("/org/apache/ctakes/coreference/models/mention-cluster/model.jar")); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getMentionClusterCoreferenceDescription() throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); // Add markables using syntax: (nouns and pronouns) builder.add(AnalysisEngineFactory.createEngineDescription(DeterministicMarkableAnnotator.class)); builder.add(getMentionClusterResolverDescription()); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getStandardChunkAdjusterAnnotator() throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); // adjust NP in NP NP to span both builder.add( ChunkAdjuster.createAnnotatorDescription( new String[] { "NP", "NP" }, 1 ) ); // adjust NP in NP PP NP to span all three builder.add( ChunkAdjuster.createAnnotatorDescription( new String[] { "NP", "PP", "NP" }, 2 ) ); return builder.createAggregateDescription(); }
public static AnalysisEngineDescription getStandardChunkAdjusterAnnotator() throws ResourceInitializationException { AggregateBuilder builder = new AggregateBuilder(); // adjust NP in NP NP to span both builder.add( ChunkAdjuster.createAnnotatorDescription( new String[] { "NP", "NP" }, 1 ) ); // adjust NP in NP PP NP to span all three builder.add( ChunkAdjuster.createAnnotatorDescription( new String[] { "NP", "PP", "NP" }, 2 ) ); return builder.createAggregateDescription(); }
public static void main(String[] args) throws ResourceInitializationException, SAXException, IOException { AggregateBuilder aggregateBuilder = new AggregateBuilder(); aggregateBuilder.add(SimpleSegmentAnnotator.createAnnotatorDescription()); aggregateBuilder.add(SentenceDetectorAnnotatorBIO.getDescription(sentModelPath)); aggregateBuilder.createAggregateDescription().toXML(new FileWriter("desc/analysis_engine/SentenceAnnotatorBIOAggregate.xml")); SentenceDetectorAnnotatorBIO.getDescription(sentModelPath).toXML(new FileWriter("desc/analysis_engine/SentenceDetectorAnnotatorBIO.xml")); }
private AnalysisEngineDescription buildPipeline(int stageId, Iterable<AnyObject> pipeline, FlowControllerDescription fcd) throws Exception { AggregateBuilder builder = new AggregateBuilder(null, null, fcd); int phase = 1; for (AnyObject aeDescription : pipeline) { AnalysisEngineDescription description = buildComponent(stageId, phase, aeDescription); builder.add(description); phase++; } return builder.createAggregateDescription(); }