Package de.l3s.boilerpipe.filters.english

The BoilerpipeFilters in this package have only been tested on English text.

See:
          Description

Class Summary
DensityRulesClassifier Classifies TextBlocks as content/not-content through rules that have been determined using the C4.8 machine learning algorithm, as described in the paper "Boilerplate Detection using Shallow Text Features", particularly using text densities and link densities.
IgnoreBlocksAfterContentFilter Marks all blocks as "non-content" that occur after blocks that have been marked DefaultLabels.INDICATES_END_OF_TEXT.
IgnoreBlocksAfterContentFromEndFilter Marks all blocks as "non-content" that occur after blocks that have been marked DefaultLabels.INDICATES_END_OF_TEXT, and after any content block.
KeepLargestFulltextBlockFilter Keeps the largest TextBlock only (by the number of words).
MinFulltextWordsFilter Keeps only those content blocks which contain at least k full-text words (measured by HeuristicFilterBase.getNumFullTextWords(TextBlock)). k is 30 by default.
NumWordsRulesClassifier Classifies TextBlocks as content/not-content through rules that have been determined using the C4.8 machine learning algorithm, as described in the paper "Boilerplate Detection using Shallow Text Features" (WSDM 2010), particularly using number of words per block and link density per block.
TerminatingBlocksFinder Finds blocks which are potentially indicating the end of an article text and marks them with DefaultLabels.INDICATES_END_OF_TEXT.
 

Package de.l3s.boilerpipe.filters.english Description

The BoilerpipeFilters in this package have only been tested on English text.

That is, they will probably work with other Western languages, but maybe need some parameter tuning to perform well.