ws.palladian.extraction.entity.tagger

Class IllinoisNer

java.lang.Object

ws.palladian.extraction.entity.NamedEntityRecognizer

ws.palladian.extraction.entity.TrainableNamedEntityRecognizer

ws.palladian.extraction.entity.tagger.IllinoisNer

All Implemented Interfaces:

Tagger

public class IllinoisNer
extends TrainableNamedEntityRecognizer

This class wraps the Learning Java Based Illinois Named Entity Tagger. It uses conditional random fields for tagging. The implementation is in an external library and the approach is explained in the following paper by L. Ratinov and D. Roth: "Design Challenges and Misconceptions in Named Entity Recognition", CoNLL 2009.

Author:

David Urbansky, Philipp Katz

See Also:

Illinois Named Entity Tagger

Field Summary

Fields

Modifier and Type	Field and Description
static int	DEFAULT_TRAINING_ROUNDS The default number of training rounds.

Constructor Summary

Constructors

Constructor and Description
IllinoisNer() Create a new IllinoisNer using the automatic convergence criterion for training.
IllinoisNer(int trainingRounds) Create a new IllinoisNer using specified number of iterations for training.

Method Summary

Modifier and Type	Method and Description
List<Annotation>	getAnnotations(String inputText)
String	getModelFileEnding()
String	getName()
boolean	loadModel(String configModelFilePath)
boolean	setsModelFileEndingAutomatically()
boolean	train(String trainingFilePath, String modelFilePath)

Methods inherited from class ws.palladian.extraction.entity.TrainableNamedEntityRecognizer

getModelFileEndingIfNotSetAutomatically, oneModelPerConcept, train, train

Methods inherited from class ws.palladian.extraction.entity.NamedEntityRecognizer

evaluate, evaluate, evaluate, evaluate, getTaggingFormat, setTaggingFormat, tag

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_TRAINING_ROUNDS

public static final int DEFAULT_TRAINING_ROUNDS

The default number of training rounds.

See Also:

Constant Field Values

Constructor Detail

IllinoisNer

public IllinoisNer(int trainingRounds)

Create a new IllinoisNer using specified number of iterations for training.

Parameters:

trainingRounds - The number of iterations for training, greater zero, or -1 to use an automatic convergence criterion.

IllinoisNer

public IllinoisNer()

Create a new IllinoisNer using the automatic convergence criterion for training.

Method Detail

getModelFileEnding

public String getModelFileEnding()

Specified by:

getModelFileEnding in class TrainableNamedEntityRecognizer

setsModelFileEndingAutomatically

public boolean setsModelFileEndingAutomatically()

Specified by:

setsModelFileEndingAutomatically in class TrainableNamedEntityRecognizer

train

public boolean train(String trainingFilePath,
                     String modelFilePath)

Specified by:

train in class TrainableNamedEntityRecognizer

loadModel

public boolean loadModel(String configModelFilePath)

Specified by:

loadModel in class TrainableNamedEntityRecognizer

getAnnotations

public List<Annotation> getAnnotations(String inputText)

Specified by:

getAnnotations in interface Tagger

Specified by:

getAnnotations in class NamedEntityRecognizer

getName

public String getName()

Specified by:

getName in class NamedEntityRecognizer