class TensorflowBert extends Serializable

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:

Linear Supertypes
Serializable, Serializable, AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. TensorflowBert
  2. Serializable
  3. Serializable
  4. AnyRef
  5. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new TensorflowBert(tensorflowWrapper: TensorflowWrapper, sentenceStartTokenId: Int, sentenceEndTokenId: Int, configProtoBytes: Option[Array[Byte]] = None, signatures: Option[Map[String, String]] = None)

    tensorflowWrapper

    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

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. val _tfBertSignatures: Map[String, String]
  5. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  6. def calculateEmbeddings(sentences: Seq[WordpieceTokenizedSentence], originalTokenSentences: Seq[TokenizedSentence], batchSize: Int, maxSentenceLength: Int, caseSensitive: Boolean): Seq[WordpieceEmbeddingsSentence]
  7. def calculateSentenceEmbeddings(tokens: Seq[WordpieceTokenizedSentence], sentences: Seq[Sentence], batchSize: Int, maxSentenceLength: Int, isLong: Boolean = false): Seq[Annotation]
  8. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  9. def encode(sentences: Seq[(WordpieceTokenizedSentence, Int)], maxSequenceLength: Int): Seq[Array[Int]]

    Encode the input sequence to indexes IDs adding padding where necessary

  10. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  11. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  12. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  13. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  14. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  15. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  16. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  17. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  18. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  19. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  20. def tag(batch: Seq[Array[Int]]): Seq[Array[Array[Float]]]
  21. def tagSentence(batch: Seq[Array[Int]]): Array[Array[Float]]
  22. def tagSentenceSBert(batch: Seq[Array[Int]]): Array[Array[Float]]
  23. val tensorflowWrapper: TensorflowWrapper
  24. def toString(): String
    Definition Classes
    AnyRef → Any
  25. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  26. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  27. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped