TensorflowBert

BERT (Bidirectional Encoder Representations from Transformers) provides dense vector representations for natural language by using a deep, pre-trained neural network with the Transformer architecture

See https://github.com/JohnSnowLabs/spark-nlp/blob/master/src/test/scala/com/johnsnowlabs/nlp/embeddings/BertEmbeddingsTestSpec.scala for further reference on how to use this API. Sources:

0 : corresponds to first layer (embeddings)

-1 : corresponds to last layer

2 : second-to-last layer

Linear Supertypes

Serializable, Serializable, AnyRef, Any

Instance Constructors

new TensorflowBert(tensorflow: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, configProtoBytes: Option[Array[Byte]] = None)

tensorflow
Bert Model wrapper with TensorFlow Wrapper
sentenceStartTokenId
Id of sentence start Token
sentenceEndTokenId
Id of sentence end Token.
configProtoBytes
Configuration for TensorFlow session Paper: https://arxiv.org/abs/1810.04805 Source: https://github.com/google-research/bert

Value Members

final def !=(arg0: Any): Boolean

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

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def calculateEmbeddings(sentences: Seq[WordpieceTokenizedSentence], originalTokenSentences: Seq[TokenizedSentence], poolingLayer: Int, batchSize: Int, maxSentenceLength: Int, dimension: Int, caseSensitive: Boolean): Seq[WordpieceEmbeddingsSentence]
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def encode(sentence: WordpieceTokenizedSentence, maxSentenceLength: Int): Array[Int]
final def eq(arg0: AnyRef): Boolean

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

Definition Classes
AnyRef → Any
def extractPoolingLayer(layer: Int, dimension: Int): String
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

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

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

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

Definition Classes
AnyRef
def tag(batch: Seq[Array[Int]], embeddingsKey: String, maxSentenceLength: Int): Seq[Array[Array[Float]]]
val tensorflow: TensorflowWrapper

Bert Model wrapper with TensorFlow Wrapper
def toString(): String

Definition Classes
AnyRef → Any
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( ... )

Related Doc: package tensorflow

class TensorflowBert extends Serializable

Instance Constructors

new TensorflowBert(tensorflow: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, configProtoBytes: Option[Array[Byte]] = None)

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def calculateEmbeddings(sentences: Seq[WordpieceTokenizedSentence], originalTokenSentences: Seq[TokenizedSentence], poolingLayer: Int, batchSize: Int, maxSentenceLength: Int, dimension: Int, caseSensitive: Boolean): Seq[WordpieceEmbeddingsSentence]

def clone(): AnyRef

def encode(sentence: WordpieceTokenizedSentence, maxSentenceLength: Int): Array[Int]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def extractPoolingLayer(layer: Int, dimension: Int): String

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

final def synchronized[T0](arg0: ⇒ T0): T0

def tag(batch: Seq[Array[Int]], embeddingsKey: String, maxSentenceLength: Int): Seq[Array[Array[Float]]]

val tensorflow: TensorflowWrapper

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped