cc.mallet.extract
Class BIOTokenizationFilter

java.lang.Object
  extended by cc.mallet.extract.BIOTokenizationFilter
All Implemented Interfaces:
TokenizationFilter, java.io.Serializable
Direct Known Subclasses:
BIOTokenizationFilterWithTokenIndices

public class BIOTokenizationFilter
extends java.lang.Object
implements TokenizationFilter, java.io.Serializable

Created: Nov 12, 2004

Version:
$Id: BIOTokenizationFilter.java,v 1.1 2007/10/22 21:37:44 mccallum Exp $
Author:
Serialized Form

Constructor Summary
BIOTokenizationFilter()
           
 
Method Summary
 LabeledSpans constructLabeledSpans(LabelAlphabet dict, java.lang.Object document, Label backgroundTag, Tokenization input, Sequence seq)
          Converts a the sequence of labels into a set of labeled spans.
protected  Span createSpan(Tokenization input, int startTokenIdx, int endTokenIdx)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

BIOTokenizationFilter

public BIOTokenizationFilter()
Method Detail

constructLabeledSpans

public LabeledSpans constructLabeledSpans(LabelAlphabet dict,
                                          java.lang.Object document,
                                          Label backgroundTag,
                                          Tokenization input,
                                          Sequence seq)
Description copied from interface: TokenizationFilter
Converts a the sequence of labels into a set of labeled spans. Essentially, this converts the output of sequence labeling into an extraction output.

Specified by:
constructLabeledSpans in interface TokenizationFilter
Returns:

createSpan

protected Span createSpan(Tokenization input,
                          int startTokenIdx,
                          int endTokenIdx)