Examples of org.apache.uima.fit.factory.AggregateBuilder

org.apache.uima.fit.factory.AggregateBuilder

This builder makes it easier to create an aggregate analysis engine. A typical use-case would involve initializing this builder with your preferred type system and type priorities (the latter may be null). This is followed by adding analysis engine descriptions one at a time until done. This makes it easy to have runtime decisions determine how the aggregate engine should be built. Finally, one of the create methods are called and an AnalysisEngine or AnalysisEngineDescription is returned.

This is an example taken from our test cases:

 import static org.apache.uima.fit.factory.AnalysisEngineFactory.createPrimitiveDescription; AggregateBuilder builder = new AggregateBuilder(); builder.add(createPrimitiveDescription(Annotator1.class, typeSystemDescription), ViewNames.PARENTHESES_VIEW, "A"); builder.add(createPrimitiveDescription(Annotator2.class, typeSystemDescription), ViewNames.SORTED_VIEW, "B", ViewNames.SORTED_PARENTHESES_VIEW, "C", ViewNames.PARENTHESES_VIEW, "A"); builder.add(createPrimitiveDescription(Annotator3.class, typeSystemDescription), ViewNames.INITIAL_VIEW, "B"); AnalysisEngine aggregateEngine = builder.createAggregate();


    ruta.getAnalysisEngineMetaData()
            .getTypeSystem()
            .addType("org.apache.uima.T1", "Type for Testing", "uima.tcas.Annotation");


    final AggregateBuilder builder = new AggregateBuilder();
    builder.add(ruta, "_InitialView", "text");


    return builder.createAggregate();
  }

View Full Code Here

    // This resource is shared between the UimaAcronymAnnotator and UimaMeetingAnnotator
    ExternalResourceDescription resource = createExternalResourceDescription(
            StringMapResource_impl.class,
            "file:src/main/resources/org/apache/uima/fit/examples/tutorial/ex6/uimaAcronyms.txt");


    AggregateBuilder builder = new AggregateBuilder();
    builder.add(createEngineDescription(UimaAcronymAnnotator.class,
            UimaAcronymAnnotator.RES_ACRONYM_TABLE, resource));
    builder.add(createEngineDescription(UimaMeetingAnnotator.class,
            UimaMeetingAnnotator.RES_UIMA_TERM_TABLE, resource));
    AnalysisEngine engine = createEngine(builder.createAggregateDescription());


    JCas jCas = engine.newJCas();
    jCas.setDocumentText("Let's meet to talk about the CPE. The meeting is over at Yorktown 01-144");
    new Meeting(jCas, 0, 33).addToIndexes();

View Full Code Here


    ExternalResourceDescription resource = createExternalResourceDescription(
            StringMapResource_impl.class,
            "file:org/apache/uima/fit/examples/tutorial/ex6/uimaAcronyms.txt");


    AggregateBuilder builder = new AggregateBuilder();
    builder.add(createEngineDescription(UimaAcronymAnnotator.class,
            UimaAcronymAnnotator.RES_ACRONYM_TABLE, resource));
    builder.add(createEngineDescription(UimaMeetingAnnotator.class,
            UimaMeetingAnnotator.RES_UIMA_TERM_TABLE, resource));
    AnalysisEngineDescription aggregate = builder.createAggregateDescription();


    aggregate.toXML(new FileOutputStream(new File(outputDirectory, "UimaMeetingDetectorTAE.xml")));
  }

View Full Code Here

    // The lineReader simply copies the lines from the input file into the
    // default view - one line per CAS
    CollectionReader lineReader = CollectionReaderFactory.createReader(LineReader.class,
            LineReader.PARAM_INPUT_FILE, samplePosFileName);


    AggregateBuilder builder = new AggregateBuilder();


    // The goldTagger parses the data in the default view into Token objects
    // along with their part-of-speech tags which will be added to the
    // GOLD_VIEW
    AnalysisEngineDescription goldTagger = AnalysisEngineFactory.createEngineDescription(
            GoldTagger.class);
    builder.add(goldTagger);


    // The textCopier creates the SYSTEM_VIEW and set the text of this view
    // to that of the text found in GOLD_VIEW
    AnalysisEngineDescription textCopier = AnalysisEngineFactory.createEngineDescription(
            ViewTextCopierAnnotator.class,
            ViewTextCopierAnnotator.PARAM_SOURCE_VIEW_NAME, ViewNames.GOLD_VIEW,
            ViewTextCopierAnnotator.PARAM_DESTINATION_VIEW_NAME, ViewNames.SYSTEM_VIEW);
    builder.add(textCopier);


    // The sentenceAndTokenCopier copies Token and Sentence annotations in
    // the GOLD_VIEW into the SYSTEM_VIEW
    AnalysisEngineDescription sentenceAndTokenCopier = AnalysisEngineFactory
            .createEngineDescription(SentenceAndTokenCopier.class);
    builder.add(sentenceAndTokenCopier, ViewNames.VIEW1, ViewNames.GOLD_VIEW, ViewNames.VIEW2,
            ViewNames.SYSTEM_VIEW);


    // The baselineTagger is run on the SYSTEM_VIEW
    AnalysisEngineDescription baselineTagger = AnalysisEngineFactory.createEngineDescription(
            BaselineTagger.class);
    builder.add(baselineTagger, CAS.NAME_DEFAULT_SOFA, ViewNames.SYSTEM_VIEW);


    // The evaluator will compare the part-of-speech tags in the SYSTEM_VIEW
    // with those in the GOLD_VIEW
    AnalysisEngineDescription evaluator = AnalysisEngineFactory.createEngineDescription(
            Evaluator.class);
    builder.add(evaluator);


    // The xWriter writes out the contents of each CAS (one per sentence) to
    // an XMI file. It is instructive to open one of these
    // XMI files in the CAS Visual Debugger and look at the contents of each
    // view.
    AnalysisEngineDescription xWriter = AnalysisEngineFactory.createEngineDescription(
            XmiWriter.class, XmiWriter.PARAM_OUTPUT_DIRECTORY, "target/examples/pos/xmi");
    builder.add(xWriter);


    // runs the collection reader and the aggregate AE.
    SimplePipeline.runPipeline(lineReader, builder.createAggregate());
  }

View Full Code Here

          PlainTextCombinationReader.PARAM_LANGUAGE, "en",
          PlainTextCombinationReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
  
      AnalysisEngineDescription seg = createEngineDescription(
          BreakIteratorSegmenter.class);
      AggregateBuilder builder = new AggregateBuilder();
      builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
      builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
      AnalysisEngine aggr_seg = builder.createAggregate();
      
//      AnalysisEngineDescription tt = createPrimitiveDescription(
//          TreeTaggerPosLemmaTT4J.class,
//          TreeTaggerPosLemmaTT4J.PARAM_LANGUAGE_CODE, "en");    
//      builder = new AggregateBuilder();

View Full Code Here

            SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
    
        AnalysisEngineDescription seg = createEngineDescription(
            BreakIteratorSegmenter.class);
        
        AggregateBuilder builder = new AggregateBuilder();
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_seg = builder.createAggregate();
        
//        AnalysisEngineDescription tt = createPrimitiveDescription(
//            TreeTaggerPosLemmaTT4J.class,
//            TreeTaggerPosLemmaTT4J.PARAM_LANGUAGE_CODE, "en");    
//        builder = new AggregateBuilder();

View Full Code Here

            SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString(), SemEvalCorpusReader.PARAM_LANGUAGE, "en");
    
        // Tokenization
        AnalysisEngineDescription seg = createEngineDescription(
            BreakIteratorSegmenter.class);
        AggregateBuilder builder = new AggregateBuilder();
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_seg = builder.createAggregate();
        
        // POS Tagging
        AnalysisEngineDescription pos = createEngineDescription(
            OpenNlpPosTagger.class,
            OpenNlpPosTagger.PARAM_LANGUAGE, "en");    
        builder = new AggregateBuilder();
        builder.add(pos, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(pos, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_pos = builder.createAggregate();
        
        // Lemmatization
        AnalysisEngineDescription lem = createEngineDescription(
//            StanfordLemmatizer.class);
            GateLemmatizer.class);
        builder = new AggregateBuilder();
        builder.add(lem, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(lem, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_lem = builder.createAggregate();
        
        // Stopword Filter (if applicable)
        AnalysisEngineDescription stopw = createEngineDescription(
            StopwordFilter.class,
            StopwordFilter.PARAM_STOPWORD_LIST, "classpath:/stopwords/stopwords_english_punctuation.txt",
            StopwordFilter.PARAM_ANNOTATION_TYPE_NAME, Lemma.class.getName(),
            StopwordFilter.PARAM_STRING_REPRESENTATION_METHOD_NAME, "getValue");
        builder = new AggregateBuilder();
        builder.add(stopw, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(stopw, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_stopw = builder.createAggregate();
    
        // Similarity Scorer
        AnalysisEngine scorer = createEngine(SimilarityScorer.class,
            SimilarityScorer.PARAM_NAME_VIEW_1, CombinationReader.VIEW_1,
            SimilarityScorer.PARAM_NAME_VIEW_2, CombinationReader.VIEW_2,

View Full Code Here

          SemEvalCorpusReader.PARAM_LANGUAGE, "en",
          SemEvalCorpusReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
      
      AnalysisEngineDescription seg = createEngineDescription(BreakIteratorSegmenter.class);
      
      AggregateBuilder builder = new AggregateBuilder();
      builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
      builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
      AnalysisEngine aggr_seg = builder.createAggregate();
  
      AnalysisEngine scorer = createEngine(SimilarityScorer.class,
            SimilarityScorer.PARAM_NAME_VIEW_1, CombinationReader.VIEW_1,
            SimilarityScorer.PARAM_NAME_VIEW_2, CombinationReader.VIEW_2,
            SimilarityScorer.PARAM_SEGMENT_FEATURE_PATH, Document.class.getName(),

View Full Code Here

//        PlainTextCombinationReader.PARAM_INPUT_DIR, "classpath:/datasets/test/plaintext",
//        PlainTextCombinationReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());


    AnalysisEngineDescription seg = createEngineDescription(BreakIteratorSegmenter.class);
    
    AggregateBuilder builder = new AggregateBuilder();
    builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
    builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
    AnalysisEngine aggr_seg = builder.createAggregate();


    AnalysisEngine scorer = createEngine(SimilarityScorer.class,
          SimilarityScorer.PARAM_NAME_VIEW_1, CombinationReader.VIEW_1,
          SimilarityScorer.PARAM_NAME_VIEW_2, CombinationReader.VIEW_2,
          SimilarityScorer.PARAM_SEGMENT_FEATURE_PATH, Document.class.getName(),

View Full Code Here

            ShortAnswerGradingReader.PARAM_INPUT_DIR, "classpath:/datasets/mm09",
            ShortAnswerGradingReader.PARAM_COMBINATION_STRATEGY, CombinationStrategy.SAME_ROW_ONLY.toString());
    
        AnalysisEngineDescription seg = createEngineDescription(BreakIteratorSegmenter.class);
        
        AggregateBuilder builder = new AggregateBuilder();
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_1);
        builder.add(seg, CombinationReader.INITIAL_VIEW, CombinationReader.VIEW_2);
        AnalysisEngine aggr_seg = builder.createAggregate();
        
//        AnalysisEngineDescription tt = createPrimitiveDescription(
//            TreeTaggerPosLemmaTT4J.class,
//            TreeTaggerPosLemmaTT4J.PARAM_LANGUAGE_CODE, "en");    
//        builder = new AggregateBuilder();

View Full Code Here

0 1

TOP

Related Classes of org.apache.uima.fit.factory.AggregateBuilder

dkpro.similarity.example.WithDKPro

org.apache.uima.fit.examples.experiment.pos.RunExperiment

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.