opennlp.tools.lang.english
Class TreebankChunker

java.lang.Object
  opennlp.tools.chunker.ChunkerME
      opennlp.tools.lang.english.TreebankChunker

All Implemented Interfaces:

Chunker

public class TreebankChunker
extends ChunkerME

This is a chunker based on the CONLL chunking task which uses Penn Treebank constituents as the basis for the chunks. See http://cnts.uia.ac.be/conll2000/chunking/ for data and task definition.

Author:

Tom Morton

Field Summary

Fields inherited from class opennlp.tools.chunker.ChunkerME

beam, model

Constructor Summary

TreebankChunker(opennlp.maxent.MaxentModel mod)
Creates an English Treebank Chunker which uses the specified model.

TreebankChunker(opennlp.maxent.MaxentModel mod, ChunkerContextGenerator cg)
Creates an English Treebank Chunker which uses the specified model and context generator.

TreebankChunker(opennlp.maxent.MaxentModel mod, ChunkerContextGenerator cg, int beamSize)
Creates an English Treebank Chunker which uses the specified model and context generator which will be decoded using the specified beamSize.

TreebankChunker(java.lang.String modelFile)
Creates an English Treebank Chunker which uses the specified model file.

Method Summary

static void	main(java.lang.String[] args) Chunks tokenized input from stdin.
protected boolean	validOutcome(java.lang.String outcome, java.lang.String[] sequence) This method determines wheter the outcome is valid for the preceeding sequence.

Methods inherited from class opennlp.tools.chunker.ChunkerME

chunk, chunk, probs, probs, train

Methods inherited from class java.lang.Object

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

Constructor Detail

TreebankChunker

public TreebankChunker(java.lang.String modelFile)
                throws java.io.IOException

Creates an English Treebank Chunker which uses the specified model file.

Parameters:

modelFile - The name of the maxent model to be used.

Throws:

java.io.IOException - When the model file can't be open or read.

TreebankChunker

public TreebankChunker(opennlp.maxent.MaxentModel mod)

Creates an English Treebank Chunker which uses the specified model.

Parameters:

mod - The maxent model to be used.

TreebankChunker

public TreebankChunker(opennlp.maxent.MaxentModel mod,
                       ChunkerContextGenerator cg)

Creates an English Treebank Chunker which uses the specified model and context generator.

Parameters:

mod - The maxent model to be used.

cg - The context generator to be used.

TreebankChunker

public TreebankChunker(opennlp.maxent.MaxentModel mod,
                       ChunkerContextGenerator cg,
                       int beamSize)

Creates an English Treebank Chunker which uses the specified model and context generator which will be decoded using the specified beamSize.

Parameters:

mod - The maxent model to be used.

cg - The context generator to be used.

beamSize - The size of the beam used for decoding.

Method Detail

validOutcome

protected boolean validOutcome(java.lang.String outcome,
                               java.lang.String[] sequence)

Description copied from class: ChunkerME

This method determines wheter the outcome is valid for the preceeding sequence. This can be used to implement constraints on what sequences are valid.

Overrides:

validOutcome in class ChunkerME

Parameters:

outcome - The outcome.

sequence - The precceding sequence of outcome assignments.

Returns:

true is the outcome is valid for the sequence, false otherwise.

main

public static void main(java.lang.String[] args)
                 throws java.io.IOException

Chunks tokenized input from stdin.
Usage: java opennlp.tools.chunker.EnglishTreebankChunker model < tokenized_sentences

Throws:

java.io.IOException