org.carrot2.text.clustering
Class MultilingualClustering

java.lang.Object
  org.carrot2.text.clustering.MultilingualClustering

public class MultilingualClustering
extends Object

A helper for clustering multilingual collections of documents. The helper partitions the input documents by Document.LANGUAGE, clusters each such monolingual partition separately and then aggregates the partial cluster lists based on the selected MultilingualClustering.LanguageAggregationStrategy.

Nested Class Summary

static class

MultilingualClustering.LanguageAggregationStrategy Defines how monolingual partial clusters will be combined to form final results.

Field Summary

LanguageCode	defaultLanguage Default clustering language.
MultilingualClustering.LanguageAggregationStrategy	languageAggregationStrategy Language aggregation strategy.

Constructor Summary

MultilingualClustering()

Method Summary

List<Cluster>

process(List<Document> documents, IMonolingualClusteringAlgorithm algorithm)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

languageAggregationStrategy

public MultilingualClustering.LanguageAggregationStrategy languageAggregationStrategy

Language aggregation strategy. Determines how clusters generated for individual languages should be combined to form the final result. Please see MultilingualClustering.LanguageAggregationStrategy for the list of available options.

Attribute level:

Medium

Attribute group:

Multilingual clustering

defaultLanguage

public LanguageCode defaultLanguage

Default clustering language. The default language to use for documents with undefined Document.LANGUAGE.

Attribute level:

Medium

Attribute group:

Multilingual clustering

Constructor Detail

MultilingualClustering

public MultilingualClustering()

Method Detail

process

public List<Cluster> process(List<Document> documents,
                             IMonolingualClusteringAlgorithm algorithm)