<searchComponent name="clustering" enable="${solr.clustering.enabled:true}" class="solr.clustering.ClusteringComponent" > <lst name="engine"> <str name="name">default</str> <str name="carrot.algorithm">org.carrot2.clustering.lingo.LingoClusteringAlgorithm</str> <str name="LingoClusteringAlgorithm.desiredClusterCountBase">30</str><!--2~100--> <str name="LingoClusteringAlgorithm.clusterMergingThreshold">0.70</str><!--0~1--> <str name="LingoClusteringAlgorithm.scoreWeight">0</str><!--0~1--> <str name="LingoClusteringAlgorithm.labelAssigner">org.carrot2.clustering.lingo.SimpleLabelAssigner</str><!--org.carrot2.clustering.lingo.UniqueLabelAssigner --> <str name="LingoClusteringAlgorithm.phraseLabelBoost">1.5</str><!--0~10--> <str name="LingoClusteringAlgorithm.phraseLengthPenaltyStart">8</str><!--2~8--> <str name="LingoClusteringAlgorithm.phraseLengthPenaltyStop">8</str><!--2~8--> <str name="TermDocumentMatrixReducer.factorizationQuality">HIGH</str><!--LOW,MEDIUM,HIGH--> <!-- org.carrot2.matrix.factorization.PartialSingularValueDecompositionFactory org.carrot2.matrix.factorization.NonnegativeMatrixFactorizationEDFactory org.carrot2.matrix.factorization.NonnegativeMatrixFactorizationKLFactory org.carrot2.matrix.factorization.LocalNonnegativeMatrixFactorizationFactory org.carrot2.matrix.factorization.KMeansMatrixFactorizationFactory --> <str name="TermDocumentMatrixReducer.factorizationFactory">org.carrot2.matrix.factorization.NonnegativeMatrixFactorizationEDFactory</str> <str name="TermDocumentMatrixBuilder.maximumMatrixSize">37500</str><!--MinValue5000--> <str name="TermDocumentMatrixBuilder.titleWordsBoost">2.0</str><!--2~10--> <str name="TermDocumentMatrixBuilder.maxWordDf">0.9</str><!--0~1--> <!--org.carrot2.text.vsm.LogTfIdfTermWeighting,org.carrot2.text.vsm.LinearTfIdfTermWeighting--> <str name="TermDocumentMatrixBuilder.termWeighting">org.carrot2.text.vsm.TfTermWeighting</str> <str name="MultilingualClustering.defaultLanguage">CHINESE_SIMPLIFIED</str> <str name="MultilingualClustering.languageAggregationStrategy">org.carrot2.text.clustering.MultilingualClustering.LanguageAggregationStrategy.FLATTEN_MAJOR_LANGUAGE </str><!--FLATTEN_ALL,FLATTEN_NONE--> <str name="GenitiveLabelFilter.enabled">true</str> <str name="StopWordLabelFilter.enabled">true</str> <str name="NumericLabelFilter.enabled">true</str> <str name="QueryLabelFilter.enabled">true</str> <str name="MinLengthLabelFilter.enabled">true</str> <str name="StopLabelFilter.enabled">true</str> <str name="CompleteLabelFilter.enabled">true</str> <str name="CompleteLabelFilter.labelOverrideThreshold">0.65</str><!--0~1--> <str name="DocumentAssigner.exactPhraseAssignment">false</str> <str name="DocumentAssigner.minClusterSize">2</str><!--1~100--> <str name="merge-resources">true</str> <str name="CaseNormalizer.dfThreshold">1</str><!--1~100--> <str name="PhraseExtractor.dfThreshold">1</str><!--1~100--> <str name="carrot.lexicalResourcesDir">clustering/carrot2</str> <str name="SolrDocumentSource.solrIdFieldName">id</str> </lst> </searchComponent> |