RelationExtractionApproach

Companion object RelationExtractionApproach

class RelationExtractionApproach extends GenericClassifierApproach with HandleExceptionParams

Trains a TensorFlow model for relation extraction.

For pretrained models, see the documentation of RelationExtractionModel.

A suitable Tensorflow graph is selected automatically from the graphs embedded in the library, based on the size of the feature vectors and on the number of relation labels of the training dataset. A custom graph, created with the TfGraphBuilder annotator or with the tf_graph module, can still be used by setting the path of the graph with setModelFile, or the folder holding several graphs with setGraphFolder.

If the parameter relationDirectionCol is set, the model will be trained using the direction information (see the parameter decription for details). Otherwise, the model won't have direction between the relation of the entities. After training a model (using the .fit() method), the resulting object is of class RelationExtractionModel.

Example

Defining pipeline stages to extract entities first

val documentAssembler = new DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")

val tokenizer = new Tokenizer()
  .setInputCols(Array("document"))
  .setOutputCol("tokens")

val embedder = WordEmbeddingsModel
  .pretrained("embeddings_clinical", "en", "clinical/models")
  .setInputCols(Array("document", "tokens"))
  .setOutputCol("embeddings")

val posTagger = PerceptronModel
  .pretrained("pos_clinical", "en", "clinical/models")
  .setInputCols(Array("document", "tokens"))
  .setOutputCol("posTags")

val nerTagger = MedicalNerModel
  .pretrained("ner_events_clinical", "en", "clinical/models")
  .setInputCols(Array("document", "tokens", "embeddings"))
  .setOutputCol("ner_tags")

val nerConverter = new NerConverter()
  .setInputCols(Array("document", "tokens", "ner_tags"))
  .setOutputCol("nerChunks")

val depencyParser = DependencyParserModel
  .pretrained("dependency_conllu", "en")
  .setInputCols(Array("document", "posTags", "tokens"))
  .setOutputCol("dependencies")

Then define RelationExtractionApproach and training parameters

val re = new RelationExtractionApproach()
  .setInputCols(Array("embeddings", "posTags", "train_ner_chunks", "dependencies"))
  .setOutputCol("relations_t")
  .setLabelColumn("target_rel")
  .setEpochsNumber(300)
  .setBatchSize(200)
  .setlearningRate(0.001f)
  .setModelFile("path/to/graph_file.pb")
  .setFixImbalance(true)
  .setValidationSplit(0.05f)
  .setFromEntity("from_begin", "from_end", "from_label")
  .setToEntity("to_begin", "to_end", "to_label")

val finisher = new Finisher()
  .setInputCols(Array("relations_t"))
  .setOutputCols(Array("relations"))
  .setCleanAnnotations(false)
  .setValueSplitSymbol(",")
  .setAnnotationSplitSymbol(",")
  .setOutputAsArray(false)

Define complete pipeline and start training

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    tokenizer,
    embedder,
    posTagger,
    nerTagger,
    nerConverter,
    depencyParser,
    re,
    finisher))

val model = pipeline.fit(trainData)

See also: RelationExtractionModel for pretrained models and how to use it

Linear Supertypes

GenericClassifierApproach, CheckLicense, HandleExceptionParams, GenericClassifierParams, AnnotatorApproach[GenericClassifierModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[GenericClassifierModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any

Known Subclasses

RelationExtractionApproach

Ordering

Grouped
Alphabetic
By Inheritance

Inherited

RelationExtractionApproach
GenericClassifierApproach
CheckLicense
HandleExceptionParams
GenericClassifierParams
AnnotatorApproach
CanBeLazy
DefaultParamsWritable
MLWritable
HasOutputAnnotatorType
HasOutputAnnotationCol
HasInputAnnotationCols
Estimator
PipelineStage
Logging
Params
Serializable
Serializable
Identifiable
AnyRef
Any

Hide All
Show All

Visibility

Public
All

Instance Constructors

new RelationExtractionApproach()
new RelationExtractionApproach(uid: String)
uid
a unique identifier for the instantiated AnnotatorModel

Type Members

type AnnotatorType = String

Definition Classes
HasOutputAnnotatorType

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def $[T](param: Param[T]): T

Attributes
protected
Definition Classes
Params
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): GenericClassifierModel

Attributes
protected
Definition Classes
AnnotatorApproach
final def asInstanceOf[T0]: T0

Definition Classes
Any
val batchSize: IntParam
Batch size
Batch size

Definition Classes
GenericClassifierParams
def beforeTraining(spark: SparkSession): Unit

Definition Classes
GenericClassifierApproach → AnnotatorApproach
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

Attributes
protected
Definition Classes
HasInputAnnotationCols
def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String], metadata: Option[Map[String, Value]]): Unit

Definition Classes
CheckLicense
def checkValidScope(scope: String): Unit

Definition Classes
CheckLicense
def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit

Definition Classes
CheckLicense
def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit

Definition Classes
CheckLicense
final def clear(param: Param[_]): RelationExtractionApproach.this.type

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws( ... ) @native()
final def copy(extra: ParamMap): Estimator[GenericClassifierModel]

Definition Classes
AnnotatorApproach → Estimator → PipelineStage → Params
def copyValues[T <: Params](to: T, extra: ParamMap): T

Attributes
protected
Definition Classes
Params
var customLabels: CustomLabels
Custom relation labels
val datasetInfo: Param[String]
Descriptive information about the dataset being used.
Descriptive information about the dataset being used.

Definition Classes
GenericClassifierParams
final def defaultCopy[T <: Params](extra: ParamMap): T

Attributes
protected
Definition Classes
Params
val description: String
Trains TensorFlow model for multi-class text classification
Trains TensorFlow model for multi-class text classification

Definition Classes
RelationExtractionApproach → GenericClassifierApproach → AnnotatorApproach
val directionSensitive: BooleanParam
If it is true, only relations in the form of "ENTITY1-ENTITY2" will be considered, If it is false, both "ENTITY1-ENTITY2" and "ENTITY2-ENTITY1" relations will be considered,
val doExceptionHandling: BooleanParam
If true, exceptions are handled.
If true, exceptions are handled. If exception causing data is passed to the model, a error annotation is emitted which has the exception message. Processing continues with the next one. This comes with a performance penalty.

Definition Classes
HandleExceptionParams
val dropout: FloatParam
Dropout coefficient.
Dropout coefficient.
It is applied to the output of the last hidden layer of the graph. Graphs without hidden layer (GenericLogRegClassifier, FewShotClassifier, GenericSVMClassifier) apply it directly to the input feature vector, so a value greater than 0 drops input features there: set it to 0 for those annotators unless input dropout is what you want.

Definition Classes
GenericClassifierParams
val epochsN: IntParam
Maximum number of epochs to train
Maximum number of epochs to train

Definition Classes
GenericClassifierParams
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def explainParam(param: Param[_]): String

Definition Classes
Params
def explainParams(): String

Definition Classes
Params
final val extraInputCols: StringArrayParam

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def extractParamMap(): ParamMap

Definition Classes
Params
final def extractParamMap(extra: ParamMap): ParamMap

Definition Classes
Params
val featureScaling: Param[String]
Feature scaling method.
Feature scaling method. Possible values are 'zscore', 'minmax' or empty (no scaling)

Definition Classes
GenericClassifierParams
val filterByTokenDistance: IntParam
filtering criterion based on number of token between entities.
filtering criterion based on number of token between entities. Model only finds relations that have fewer than the specified number of tokens between them.
def finalize(): Unit

Attributes
protected[lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def fit(dataset: Dataset[_]): GenericClassifierModel

Definition Classes
AnnotatorApproach → Estimator
def fit(dataset: Dataset[_], paramMaps: Seq[ParamMap]): Seq[GenericClassifierModel]

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], paramMap: ParamMap): GenericClassifierModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): GenericClassifierModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
val fixImbalance: BooleanParam
Fix the imbalance in the training set by replicating examples of under represented categories.
Fix the imbalance in the training set by replicating examples of under represented categories.
The class weights are only used by the loss of graphs with a softmax output (the GenericClassifier/RelationExtraction family). Graphs with a sigmoid output (logistic regression, SVM) compute their loss without them, so this parameter has no effect there.

Definition Classes
GenericClassifierParams
val fromEntityBeginCol: Param[String]
Column for beginning of 'from' entity
val fromEntityEndCol: Param[String]
Column for end of 'from' entity
val fromEntityLabelCol: Param[String]
Column for 'from' entity label
final def get[T](param: Param[T]): Option[T]

Definition Classes
Params
def getBatchSize: Int
Batch size
Batch size

Definition Classes
GenericClassifierParams
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
Annotations
@native()
def getCustomLabels: Map[String, String]
Get custom labels
def getDatasetInfo: String
get descriptive information about the dataset being used
get descriptive information about the dataset being used

Definition Classes
GenericClassifierParams
final def getDefault[T](param: Param[T]): Option[T]

Definition Classes
Params
def getDropout: Float
Dropout coefficient
Dropout coefficient

Definition Classes
GenericClassifierParams
def getExistingLabels(): Array[String]

Attributes
protected
Definition Classes
RelationExtractionApproach → GenericClassifierApproach
def getFeatureScaling: String
Get feature scaling method
Get feature scaling method

Definition Classes
GenericClassifierParams
def getFixImbalance: Boolean
Fix imbalance in training set
Fix imbalance in training set

Definition Classes
GenericClassifierParams
def getFromEntityBeginCol: String
Column for beginning of 'from' entity
def getFromEntityEndCol: String
Column for end of 'from' entity
def getFromEntityLabelCol: String
Column for 'from' entity label
def getGraphFolder: String
Folder with the TensorFlow graphs to choose the model graph from
Folder with the TensorFlow graphs to choose the model graph from

Definition Classes
GenericClassifierParams
def getInputCols: Array[String]

Definition Classes
HasInputAnnotationCols
def getLabelColumn: String
Column with label per each document
Column with label per each document

Definition Classes
GenericClassifierParams
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
def getLearningRate: Float
Learning Rate
Learning Rate

Definition Classes
GenericClassifierParams
def getMaxEpochs: Int
Maximum number of epochs to train
Maximum number of epochs to train

Definition Classes
GenericClassifierParams
def getMaxSyntacticDistance: Int
Maximal syntactic distance, as threshold (Default: 0)
def getModelFile: String
Path of the TensorFlow graph to train with, empty when it is resolved automatically
Path of the TensorFlow graph to train with, empty when it is resolved automatically

Definition Classes
GenericClassifierParams
def getMultiClass: Boolean
Gets the model multi class prediction mode
Gets the model multi class prediction mode

Definition Classes
GenericClassifierParams
final def getOrDefault[T](param: Param[T]): T

Definition Classes
Params
final def getOutputCol: String

Definition Classes
HasOutputAnnotationCol
def getOutputLogsPath: String
Get output logs path
Get output logs path

Definition Classes
GenericClassifierParams
def getOverrideExistingLabels: Boolean
Whether to override already learned labels when using a pretrained model to initialize the new model.
def getParam(paramName: String): Param[Any]

Definition Classes
Params
def getRelationDirectionCol: String
Get relation direction
def getScopeWindow: (Int, Int)
Get scope window
def getTFWrapper(inputDim: Int, outputDim: Int): TensorflowWrapper

Attributes
protected
Definition Classes
RelationExtractionApproach → GenericClassifierApproach
def getToEntityBeginCol: String
Column for beginning of 'to' entity
def getToEntityEndCol: String
Column for end of 'to' entity
def getToEntityLabelCol: String
Column for 'to' entity label
def getValidationSplit: Float
Choose the proportion of training dataset to be validated against the model on each Epoch.
Choose the proportion of training dataset to be validated against the model on each Epoch. The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

Definition Classes
GenericClassifierParams
def graphFamily: DenseClassifierGraphFamily
Family of pre-built graphs embedded in the library, used when neither modelFile nor a pretrained model is set.
Family of pre-built graphs embedded in the library, used when neither modelFile nor a pretrained model is set. Subclasses with another topology override it.

Attributes
protected
Definition Classes
GenericClassifierApproach
val graphFolder: Param[String]
Folder with TensorFlow graphs to choose the model graph from.
Folder with TensorFlow graphs to choose the model graph from.
When it is not set, the graphs embedded in the library are used. It is ignored when modelFile is set explicitly.

Definition Classes
GenericClassifierParams
final def hasDefault[T](param: Param[T]): Boolean

Definition Classes
Params
def hasParam(paramName: String): Boolean

Definition Classes
Params
def hashCode(): Int

Definition Classes
AnyRef → Any
Annotations
@native()
def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

Attributes
protected
Definition Classes
Logging
def initializeLogIfNecessary(isInterpreter: Boolean): Unit

Attributes
protected
Definition Classes
Logging
val inputAnnotatorTypes: Array[AnnotatorType]
Input annotator type : WORD_EMBEDDINGS, POS, CHUNK, DEPENDENCY
Input annotator type : WORD_EMBEDDINGS, POS, CHUNK, DEPENDENCY

Definition Classes
RelationExtractionApproach → GenericClassifierApproach → HasInputAnnotationCols
final val inputCols: StringArrayParam

Attributes
protected
Definition Classes
HasInputAnnotationCols
final def isDefined(param: Param[_]): Boolean

Definition Classes
Params
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
final def isSet(param: Param[_]): Boolean

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
val labelColumn: Param[String]
Column with label per each document
Column with label per each document

Definition Classes
GenericClassifierParams
val lazyAnnotator: BooleanParam

Definition Classes
CanBeLazy
val learningRate: FloatParam
Learning Rate
Learning Rate

Definition Classes
GenericClassifierParams
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
var maxSyntacticDistance: IntParam
Maximal syntactic distance, as threshold (Default: 0)
val modelFile: Param[String]
Path of the TensorFlow graph to train with.
Path of the TensorFlow graph to train with.
Empty by default: a graph with suitable dimensions is then selected automatically, either from graphFolder or from the graphs embedded in the library. Set it to train with one specific graph.

Definition Classes
GenericClassifierParams
def msgHelper(schema: StructType): String

Attributes
protected
Definition Classes
HasInputAnnotationCols
val multiClass: BooleanParam
If multiClass is set, the model will return all the labels with corresponding scores.
If multiClass is set, the model will return all the labels with corresponding scores. By default, multiClass is false.

Definition Classes
GenericClassifierParams
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
Annotations
@native()
final def notifyAll(): Unit

Definition Classes
AnyRef
Annotations
@native()
def onTrained(model: GenericClassifierModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val optionalInputAnnotatorTypes: Array[String]

Definition Classes
HasInputAnnotationCols
val outputAnnotatorType: String
Output annotator type : CATEGORY
Output annotator type : CATEGORY

Definition Classes
GenericClassifierApproach → HasOutputAnnotatorType
final val outputCol: Param[String]

Attributes
protected
Definition Classes
HasOutputAnnotationCol
val outputLogsPath: Param[String]
Folder path to save training logs.
Folder path to save training logs. If no path is specified, the logs won't be stored in disk. The path can be a local file path, a distributed file path (HDFS, DBFS), or a cloud storage (S3).

Definition Classes
GenericClassifierParams
val overrideExistingLabels: BooleanParam
Controls whether to override already learned lebels when using a pretrained model to initialize the new model.
Controls whether to override already learned lebels when using a pretrained model to initialize the new model. A value of true will override existing lab els.
lazy val params: Array[Param[_]]

Definition Classes
Params
val pretrainedModelPath: Param[String]
Path to an already trained RelationExtractionModel.
Path to an already trained RelationExtractionModel.
This pretrained model will be used as a starting point for training the new one. The path can be a local file path, a distributed file path (HDFS, DBFS), or a cloud storage (S3).
var relationDirectionCol: Param[String]
Relation direction column (possible values are: "none", "left" or "right").
Relation direction column (possible values are: "none", "left" or "right").
If this parameter is not set, the model will not have direction between the relation of the entities.
def resolveGraphFile(inputDim: Int, outputDim: Int): String
Resolves the graph to train with.
Resolves the graph to train with.
modelFile wins when it has been set explicitly, otherwise the best graph of graphFamily is selected, either from graphFolder or from the graphs embedded in the library.
inputDim
length of the feature vectors of the training dataset
outputDim
number of classes of the training dataset

Attributes
protected
Definition Classes
GenericClassifierApproach
def resumeTraining: Boolean

Attributes
protected
Definition Classes
RelationExtractionApproach → GenericClassifierApproach
def resumeTrainingFromModel(model: RelationExtractionModel): RelationExtractionApproach.this.type
def save(path: String): Unit

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
val scopeWindow: IntArrayParam
The scope window of the assertion (whole sentence by default)
final def set(paramPair: ParamPair[_]): RelationExtractionApproach.this.type

Attributes
protected
Definition Classes
Params
final def set(param: String, value: Any): RelationExtractionApproach.this.type

Attributes
protected
Definition Classes
Params
final def set[T](param: Param[T], value: T): RelationExtractionApproach.this.type

Definition Classes
Params
def setBatchSize(batch: Int): RelationExtractionApproach.this.type
Batch size
Batch size

Definition Classes
GenericClassifierParams
def setCustomLabels(labels: Map[String, String]): RelationExtractionApproach.this.type
Set custom labels
def setDatasetInfo(value: String): RelationExtractionApproach.this.type
set descriptive information about the dataset being used
set descriptive information about the dataset being used

Definition Classes
GenericClassifierParams
final def setDefault(paramPairs: ParamPair[_]*): RelationExtractionApproach.this.type

Attributes
protected
Definition Classes
Params
final def setDefault[T](param: Param[T], value: T): RelationExtractionApproach.this.type

Attributes
protected[org.apache.spark.ml]
Definition Classes
Params
def setDirectionSensitive(value: Boolean): RelationExtractionApproach.this.type
If it is true, only relations in the form of "ENTITY1-ENTITY2" will be considered, If it is false, both "ENTITY1-ENTITY2" and "ENTITY2-ENTITY1" relations will be considered,
def setDoExceptionHandling(value: Boolean): RelationExtractionApproach.this.type
If true, exceptions are handled.
If true, exceptions are handled. If exception causing data is passed to the model, a error annotation is emitted which has the exception message. Processing continues with the next one. This comes with a performance penalty.

Definition Classes
HandleExceptionParams
def setDropout(dropout: Float): RelationExtractionApproach.this.type
Dropout coefficient
Dropout coefficient

Definition Classes
GenericClassifierParams
def setEpochsNumber(epochs: Int): RelationExtractionApproach.this.type
Maximum number of epochs to train
Maximum number of epochs to train

Definition Classes
GenericClassifierParams
def setExtraInputCols(value: Array[String]): RelationExtractionApproach.this.type

Definition Classes
HasInputAnnotationCols
def setFeatureScaling(featureScaling: String): RelationExtractionApproach.this.type
Set the feature scaling method.
Set the feature scaling method. Possible values are 'zscore', 'minmax' or empty (no scaling)

Definition Classes
GenericClassifierParams
def setFilterByTokenDistance(value: Int): RelationExtractionApproach.this.type
filtering criterion based on number of token between entities.
filtering criterion based on number of token between entities. Model only finds relations that have fewer than the specified number of tokens between them
def setFixImbalance(fix: Boolean): RelationExtractionApproach.this.type
Fix imbalance of training set
Fix imbalance of training set

Definition Classes
GenericClassifierParams
def setFromEntity(beginCol: String, endCol: String, labelCol: String): RelationExtractionApproach.this.type
Set from entity
def setGraphFolder(path: String): RelationExtractionApproach.this.type
Set the folder with the TensorFlow graphs to choose the model graph from.
Set the folder with the TensorFlow graphs to choose the model graph from. Ignored when modelFile is set.

Definition Classes
GenericClassifierParams
final def setInputCols(value: String*): RelationExtractionApproach.this.type

Definition Classes
HasInputAnnotationCols
def setInputCols(value: Array[String]): RelationExtractionApproach.this.type

Definition Classes
HasInputAnnotationCols
def setLabelColumn(column: String): RelationExtractionApproach.this.type
Column with label per each document
Column with label per each document

Definition Classes
GenericClassifierParams
def setLazyAnnotator(value: Boolean): RelationExtractionApproach.this.type

Definition Classes
CanBeLazy
def setMaxSyntacticDistance(maxSyntacticDistance: Int): RelationExtractionApproach.this.type
Maximal syntactic distance, as threshold (Default: 0)
def setModelFile(modelFile: String): RelationExtractionApproach.this.type
Set the model file name
Set the model file name

Definition Classes
GenericClassifierParams
def setMultiClass(value: Boolean): RelationExtractionApproach.this.type
Sets the model in multi class prediction mode
Sets the model in multi class prediction mode

Definition Classes
GenericClassifierParams
final def setOutputCol(value: String): RelationExtractionApproach.this.type

Definition Classes
HasOutputAnnotationCol
def setOutputLogsPath(outputLogsPath: String): RelationExtractionApproach.this.type
Set the output log path
Set the output log path

Definition Classes
GenericClassifierParams
def setOverrideExistingLabels(value: Boolean): RelationExtractionApproach.this.type
Controls whether to override already learned labels when using a pretrained model to initialize the new model.
Controls whether to override already learned labels when using a pretrained model to initialize the new model. A value of true will override existing labels.
def setPretrainedModelPath(path: String): RelationExtractionApproach.this.type
Set the location of an already trained RelationExtractionModel, which is used as a starting point for training the new model.
def setRelationDirectionCol(value: String): RelationExtractionApproach.this.type
Set relation direction column
def setScopeWindow(window: (Int, Int)): RelationExtractionApproach.this.type
Max possible length of a sentence.
def setToEntity(beginCol: String, endCol: String, labelCol: String): RelationExtractionApproach.this.type
Set to entity
def setValidationSplit(validationSplit: Float): RelationExtractionApproach.this.type
Choose the proportion of training dataset to be validated against the model on each Epoch.
Choose the proportion of training dataset to be validated against the model on each Epoch. The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

Definition Classes
GenericClassifierParams
def setlearningRate(lr: Float): RelationExtractionApproach.this.type
Learning Rate
Learning Rate

Definition Classes
GenericClassifierParams
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
val toEntityBeginCol: Param[String]
Column for beginning of 'to' entity
val toEntityEndCol: Param[String]
Column for end of 'to' entity
val toEntityLabelCol: Param[String]
Column for 'to' entity label
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): RelationExtractionModel

Definition Classes
RelationExtractionApproach → GenericClassifierApproach → AnnotatorApproach
final def transformSchema(schema: StructType): StructType

Definition Classes
AnnotatorApproach → PipelineStage
def transformSchema(schema: StructType, logging: Boolean): StructType

Attributes
protected
Definition Classes
PipelineStage
Annotations
@DeveloperApi()
val uid: String

Definition Classes
RelationExtractionApproach → GenericClassifierApproach → Identifiable
def validate(schema: StructType): Boolean

Attributes
protected
Definition Classes
AnnotatorApproach
val validationSplit: FloatParam
The proportion of training dataset to be used as validation set.
The proportion of training dataset to be used as validation set.
The model will be validated against this dataset on each Epoch and will not be used for training. The value should be between 0.0 and 1.0.

Definition Classes
GenericClassifierParams
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... ) @native()
def write: MLWriter

Definition Classes
DefaultParamsWritable → MLWritable

Packages

RelationExtractionApproach

Companion object RelationExtractionApproach

class RelationExtractionApproach extends GenericClassifierApproach with HandleExceptionParams

Example

Instance Constructors

Type Members

Value Members

Inherited from GenericClassifierApproach

Inherited from CheckLicense

Inherited from HandleExceptionParams

Inherited from GenericClassifierParams

Inherited from AnnotatorApproach[GenericClassifierModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[GenericClassifierModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

Annotator types

Members

Parameter setters

Parameter getters

Packages

RelationExtractionApproach 

Companion object RelationExtractionApproach

class RelationExtractionApproach extends GenericClassifierApproach with HandleExceptionParams

Example

Instance Constructors

Type Members

Value Members

Inherited from GenericClassifierApproach

Inherited from CheckLicense

Inherited from HandleExceptionParams

Inherited from GenericClassifierParams

Inherited from AnnotatorApproach[GenericClassifierModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[GenericClassifierModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

Parameters

Annotator types

Members

Parameter setters

Parameter getters

RelationExtractionApproach