Package org.carrot2.text.preprocessing.filter

Class CompleteLabelFilter

java.lang.Object

org.carrot2.attrs.AttrComposite

org.carrot2.text.preprocessing.filter.CompleteLabelFilter

All Implemented Interfaces:

AcceptingVisitor, LabelFilter

public class CompleteLabelFilter
extends AttrComposite
implements LabelFilter

A filter that removes "incomplete" labels.

For example, in a collection of documents related to Data Mining, the phrase Conference on Data is incomplete in a sense that most likely it should be Conference on Data Mining or even Conference on Data Mining in Large Databases. When truncated phrase removal is enabled, the algorithm would try to remove the "incomplete" phrases like the former one and leave only the more informative variants.

See this document, page 31 for a definition of a complete phrase.

Field Summary

Fields

Modifier and Type	Field	Description
AttrDouble	labelOverrideThreshold	Truncated label threshold.

Fields inherited from class org.carrot2.attrs.AttrComposite

attributes

Constructor Summary

Constructors

Constructor	Description
CompleteLabelFilter()

Method Summary

Modifier and Type	Method	Description
void	filter(PreprocessingContext context, boolean[] acceptedStems, boolean[] acceptedPhrases)	Marks incomplete labels.

Methods inherited from class org.carrot2.attrs.AttrComposite

accept

Methods inherited from class java.lang.Object

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

Field Detail

labelOverrideThreshold

public AttrDouble labelOverrideThreshold

Truncated label threshold. Determines the strength of the truncated label filter. The lowest value means strongest truncated labels elimination, which may lead to overlong cluster labels and many unclustered documents. The highest value effectively disables the filter, which may result in short or truncated labels.

Constructor Detail

CompleteLabelFilter

public CompleteLabelFilter()

Method Detail

filter

public void filter(PreprocessingContext context,
                   boolean[] acceptedStems,
                   boolean[] acceptedPhrases)

Marks incomplete labels.

Specified by:

filter in interface LabelFilter

Parameters:

context - contains words and phrases to be filtered

acceptedStems - the filter should set to false those elements that correspond to the stems to be filtered out

acceptedPhrases - the filter should set to false those elements that correspond to the phrases to be filtered out