edu.nyu.jet.aceJet

Class TrainEventTagger

java.lang.Object

edu.nyu.jet.aceJet.TrainEventTagger

public class TrainEventTagger
extends Object

contains top-level methods for training EventTagger.

Constructor Summary

Constructors

Constructor and Description
TrainEventTagger()

Method Summary

Methods

Modifier and Type	Method and Description
static void	main(String[] args) train an ACE event tagger from a set of documents with APF files.
static void	train(EventTagger et, String fileList, int pass) trains an event tagger from a set of text and APF files.

Methods inherited from class java.lang.Object

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

Constructor Detail

TrainEventTagger

public TrainEventTagger()

Method Detail

main

public static void main(String[] args)
                 throws IOException

train an ACE event tagger from a set of documents with APF files. Takes the following arguments:

• props: Jet property file
• fileList: list of files to be processed (one per line)
• docDir: directory containing text and APF files
• outDir: directory to receive all temporary and output files (event pattern file, event and argument models, etc.)
• glarfDir: directory containing glarf triples (optional)
• glarfSuffix: file extension for glarf files

Training is done in four passes over the training corpus:

• collect patterns (trigger words and arguments)
• count how often each pattern does/does not indicate an event
• build event model
• build event coreference model

Throws:

IOException

train

public static void train(EventTagger et,
         String fileList,
         int pass)
                  throws IOException

trains an event tagger from a set of text and APF files.

Parameters:

fileList - a list of text file names, one per line. The APF file names are obtained by replacing 'sgm' by 'apf.xml'.

Throws:

IOException