de.datexis.index.encoder

Class EntityEncoder

java.lang.Object

de.datexis.annotator.AnnotatorComponent

de.datexis.encoder.Encoder

de.datexis.index.encoder.EntityEncoder

All Implemented Interfaces:

IComponent, IEncoder

public class EntityEncoder
extends Encoder

Author:

Sebastian Arnold

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	EntityEncoder.Strategy

Field Summary

Fields

Modifier and Type	Field and Description
protected static org.slf4j.Logger	log
protected org.deeplearning4j.models.paragraphvectors.ParagraphVectors	parvec
protected EntityEncoder.Strategy	strategy

Fields inherited from class de.datexis.encoder.Encoder

enableCache

Fields inherited from class de.datexis.annotator.AnnotatorComponent

id, model, modelAvailable, name, timer

Constructor Summary

Constructors

Constructor and Description
EntityEncoder(Resource paragraphVectors, EntityEncoder.Strategy strategy)

Method Summary

Modifier and Type	Method and Description
org.nd4j.linalg.api.ndarray.INDArray	encode(Span span)
org.nd4j.linalg.api.ndarray.INDArray	encode(String word)
void	encodeEach(Document doc, Annotation.Source source, Class<? extends Annotation> type) Encodes each annotation in the document and attaches the vector to it.
org.nd4j.linalg.api.ndarray.INDArray	encodeEntity(ArticleRef ref)
org.nd4j.linalg.api.ndarray.INDArray	encodeEntity(WikiDataArticle art)
org.nd4j.linalg.api.ndarray.INDArray	encodeID(String id, String fallback)
org.nd4j.linalg.api.ndarray.INDArray	encodeMention(String mention, String context)
long	getEmbeddingVectorSize()
void	loadModel(Resource paragraphVectors)
void	saveModel(Resource dir, String name)
void	trainModel(Collection<Document> documents)

Methods inherited from class de.datexis.encoder.Encoder

encode, encodeEach, encodeEach, encodeEach, encodeMatrix, isCachingEnabled, setCachingEnabled, trainModel

Methods inherited from class de.datexis.annotator.AnnotatorComponent

appendTestLog, appendTestLog, appendTrainLog, appendTrainLog, clearTestLog, clearTrainLog, getConf, getId, getModel, getName, getTestLog, getTrainLog, isModelAvailable, isModelAvailableInChildren, setConf, setId, setModel, setModelAvailable, setModelFilename, setName

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.datexis.annotator.IComponent

getEncoders, getId, getName, isModelAvailable, setEncoders

Field Detail

log

protected static final org.slf4j.Logger log

parvec

protected org.deeplearning4j.models.paragraphvectors.ParagraphVectors parvec

strategy

protected EntityEncoder.Strategy strategy

Constructor Detail

EntityEncoder

public EntityEncoder(Resource paragraphVectors,
                     EntityEncoder.Strategy strategy)
              throws IOException

Throws:

IOException

Method Detail

loadModel

public void loadModel(Resource paragraphVectors)
               throws IOException

Throws:

IOException

getEmbeddingVectorSize

public long getEmbeddingVectorSize()

encodeEntity

public org.nd4j.linalg.api.ndarray.INDArray encodeEntity(WikiDataArticle art)

encodeEntity

public org.nd4j.linalg.api.ndarray.INDArray encodeEntity(ArticleRef ref)

encodeID

public org.nd4j.linalg.api.ndarray.INDArray encodeID(String id,
                                                     String fallback)

encodeMention

public org.nd4j.linalg.api.ndarray.INDArray encodeMention(String mention,
                                                          String context)

encode

public org.nd4j.linalg.api.ndarray.INDArray encode(Span span)

encode

public org.nd4j.linalg.api.ndarray.INDArray encode(String word)

encodeEach

public void encodeEach(Document doc,
                       Annotation.Source source,
                       Class<? extends Annotation> type)

Encodes each annotation in the document and attaches the vector to it.

trainModel

public void trainModel(Collection<Document> documents)

Specified by:

trainModel in class Encoder

saveModel

public void saveModel(Resource dir,
                      String name)