edu.illinois.cs.cogcomp.lbjava.nlp.seg

Class BIOTester

java.lang.Object

edu.illinois.cs.cogcomp.lbjava.nlp.seg.BIOTester

public class BIOTester
extends Object

This class may be used to produce a detailed report of the segment by segment performance of a given classifier on given labeled testing data. Segment by segment performance is computed by using a specified Token classifier to induce the predicted segments, and then computing precision, recall, and F₁ measures on those segments. A predicted segment is judged as different than a labeled segment if the two segments start or end at different Tokens, or if they have different types.

It is assumed that both of the specified Token classifiers (one giving labels and the other giving predictions) produce discrete predicitions of the form B-type, I-type, and O to represent the beginning of a segment of type type, a token inside a segment of type type, and a token outside of any segment respectively.

It is also assumed that the specified Parser produces Tokens linked to each other via the previous and next fields inherited from LinkedChild. In order to invoke this class as a program on the command line, it must also be the case that the parser implements a constructor with a single String argument.

Command Line Usage

java edu.illinois.cs.cogcomp.lbjava.edu.illinois.cs.cogcomp.lbjava.nlp.seg.BIOTester <classifier> <labeler> <parser> <test file>

Input

The first three arguments must be fully qualified class names. The fourth is the name of a file containing labeled testing data to be parsed by the parser.

Output

The output is generated by the TestDiscrete class.

Author:

Nick Rizzolo

Field Summary

Fields

Modifier and Type	Field and Description
protected edu.illinois.cs.cogcomp.lbjava.classify.Classifier	classifier A BIO classifier that classifies Tokens.
protected edu.illinois.cs.cogcomp.lbjava.classify.Classifier	labeler A BIO classifier that produces the true labels of the Tokens.
protected edu.illinois.cs.cogcomp.lbjava.parse.Parser	parser A parser that produces Tokens.

Constructor Summary

Constructors

Constructor and Description
BIOTester(edu.illinois.cs.cogcomp.lbjava.classify.Classifier c, edu.illinois.cs.cogcomp.lbjava.classify.Classifier l, edu.illinois.cs.cogcomp.lbjava.parse.Parser p) Initializing constructor.

Method Summary

Modifier and Type	Method and Description
static void	main(String[] args) The command line program simply instantiates an object of this class and calls its test() method.
edu.illinois.cs.cogcomp.lbjava.classify.TestDiscrete	test() This method runs the tester, packaging the results in a TestDiscrete object.

Methods inherited from class java.lang.Object

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

Field Detail

classifier

protected edu.illinois.cs.cogcomp.lbjava.classify.Classifier classifier

A BIO classifier that classifies Tokens.

labeler

protected edu.illinois.cs.cogcomp.lbjava.classify.Classifier labeler

A BIO classifier that produces the true labels of the Tokens.

parser

protected edu.illinois.cs.cogcomp.lbjava.parse.Parser parser

A parser that produces Tokens.

Constructor Detail

BIOTester

public BIOTester(edu.illinois.cs.cogcomp.lbjava.classify.Classifier c,
                 edu.illinois.cs.cogcomp.lbjava.classify.Classifier l,
                 edu.illinois.cs.cogcomp.lbjava.parse.Parser p)

Initializing constructor.

Parameters:

c - The value for classifier.

l - The value for labeler.

p - The value for parser.

Method Detail

test

public edu.illinois.cs.cogcomp.lbjava.classify.TestDiscrete test()

This method runs the tester, packaging the results in a TestDiscrete object.

Returns:

The performance results.

main

public static void main(String[] args)

The command line program simply instantiates an object of this class and calls its test() method.