class BertSentenceChunkEmbeddings extends BertSentenceEmbeddings with HandleExceptionParams with HasSafeBatchAnnotate[BertSentenceEmbeddings] with CheckLicense

BERT Sentence embeddings for chunk annotations which take into account the context of the sentence the chunk appeared in. This is an extension of BertSentenceEmbeddings which combines the embedding of a chunk with the embedding of the surrounding sentence. For each input chunk annotation, it finds the corresponding sentence, computes the BERT sentence embedding of both the chunk and the sentence and averages them. The resulting embeddings are useful in cases, in which one needs a numerical representation of a text chunk which is sensitive to the context it appears in.

This model is a subclass of BertSentenceEmbeddings and shares all parameters with it. It can load any pretrained BertSentenceEmbeddings model. Available models can be found at Models Hub.

strategy parameter defines the strategy for computing embeddings. Supported strategies are: - "sentence_average": Average of sentence and chunk embeddings. - "scope_average": Average of scope and chunk embeddings. The scope is defined by the scope window. - "chunk_only": Only chunk embeddings are used. - "scope_only": Only scope embeddings are used. The scope is defined by the scope window.

Two input columns are required - chunk and sentence. The token column is optional and should be provided if "scope_only" or "scope_average" strategy is used.

val embeddings = BertSentenceChunkEmbeddings.pretrained()
  .setInputCols("sentence", "chunk")
  .setOutputCol("sentence_chunk_bert_embeddings")

The default model is "sbiobert_base_cased_mli", if no name is provided.

Sources :

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotator.SentenceDetector
import com.johnsnowlabs.nlp.embeddings.BertSentenceEmbeddings
import com.johnsnowlabs.nlp.EmbeddingsFinisher
import org.apache.spark.ml.Pipeline

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

val sentenceDetector = new SentenceDetector()
   .setInputCols("document")
   .setOutputCol("sentence")

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

val wordEmbeddings = BertEmbeddings
   .pretrained("biobert_pubmed_base_cased")
   .setInputCols(Array("sentence", "tokens"))
   .setOutputCol("word_embeddings")

val nerModel = MedicalNerModel
   .pretrained("ner_clinical_biobert", "en", "clinical/models")
   .setInputCols(Array("sentence", "tokens", "word_embeddings"))
   .setOutputCol("ner")

 val nerConverter = new NerConverter()
   .setInputCols("sentence", "tokens", "ner")
   .setOutputCol("ner_chunk")

val sentenceChunkEmbeddings = BertSentenceChunkEmbeddings
   .pretrained("sbluebert_base_uncased_mli", "en", "clinical/models")
    .setInputCols(Array("sentence", "ner_chunk"))
    .setOutputCol("sentence_chunk_embeddings")

val pipeline = new Pipeline()
     .setStages(Array(
         documentAssembler,
         sentenceDetector,
         tokenizer,
         wordEmbeddings,
         nerModel,
         nerConverter,
         sentenceChunkEmbeddings))

val sampleText = "Her Diabetes has become type 2 in the last year with her Diabetes." +
   " He complains of swelling in his right forearm."

val testDataset = Seq("").toDS.toDF("text")
val result = pipeline.fit(emptyDataset).transform(testDataset)

result
   .selectExpr("explode(sentence_chunk_embeddings) AS s")
   .selectExpr("s.result", "slice(s.embeddings, 1, 5) AS averageEmbedding")
   .show(truncate=false)

+-----------------------------+-----------------------------------------------------------------+
|                       result|                                                 averageEmbedding|
+-----------------------------+-----------------------------------------------------------------+
|Her Diabetes                 |[-0.31995273, -0.04710883, -0.28973156, -0.1294758, 0.12481072]  |
|type 2                       |[-0.027161136, -0.24613449, -0.0949309, 0.1825444, -0.2252143]   |
|her Diabetes                 |[-0.31995273, -0.04710883, -0.28973156, -0.1294758, 0.12481072]  |
|swelling in his right forearm|[-0.45139068, 0.12400375, -0.0075617577, -0.90806055, 0.12871636]|
+-----------------------------+-----------------------------------------------------------------+
See also

BertEmbeddings for token-level embeddings

BertSentenceEmbeddings for sentence-level embeddings

Annotators Main Page for a list of transformer based embeddings

Linear Supertypes
CheckLicense, HasSafeBatchAnnotate[BertSentenceEmbeddings], HandleExceptionParams, BertSentenceEmbeddings, HasEngine, HasCaseSensitiveProperties, HasStorageRef, HasEmbeddingsProperties, HasProtectedParams, WriteOnnxModel, WriteOpenvinoModel, WriteTensorflowModel, HasBatchedAnnotate[BertSentenceEmbeddings], AnnotatorModel[BertSentenceEmbeddings], CanBeLazy, RawAnnotator[BertSentenceEmbeddings], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[BertSentenceEmbeddings], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. BertSentenceChunkEmbeddings
  2. CheckLicense
  3. HasSafeBatchAnnotate
  4. HandleExceptionParams
  5. BertSentenceEmbeddings
  6. HasEngine
  7. HasCaseSensitiveProperties
  8. HasStorageRef
  9. HasEmbeddingsProperties
  10. HasProtectedParams
  11. WriteOnnxModel
  12. WriteOpenvinoModel
  13. WriteTensorflowModel
  14. HasBatchedAnnotate
  15. AnnotatorModel
  16. CanBeLazy
  17. RawAnnotator
  18. HasOutputAnnotationCol
  19. HasInputAnnotationCols
  20. HasOutputAnnotatorType
  21. ParamsAndFeaturesWritable
  22. HasFeatures
  23. DefaultParamsWritable
  24. MLWritable
  25. Model
  26. Transformer
  27. PipelineStage
  28. Logging
  29. Params
  30. Serializable
  31. Serializable
  32. Identifiable
  33. AnyRef
  34. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new BertSentenceChunkEmbeddings()
  2. new BertSentenceChunkEmbeddings(uid: String)

Type Members

  1. type AnnotationContent = Seq[Row]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType
  3. implicit class ProtectedParam[T] extends Param[T]
    Definition Classes
    HasProtectedParams

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def $[T](param: Param[T]): T
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame
    Attributes
    protected
    Definition Classes
    BertSentenceEmbeddings → AnnotatorModel
  11. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def averageEmbeddings(chunkEmbedding: Array[Float], sentenceEmbedding: Array[Float]): Array[Float]
    Attributes
    protected
  13. def batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]
    Definition Classes
    BertSentenceChunkEmbeddings → BertSentenceEmbeddings → HasBatchedAnnotate
  14. def batchProcess(rows: Iterator[_]): Iterator[Row]
    Definition Classes
    HasBatchedAnnotate
  15. val batchSize: IntParam
    Definition Classes
    HasBatchedAnnotate
  16. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  17. val caseSensitive: BooleanParam
    Definition Classes
    HasCaseSensitiveProperties
  18. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  19. def checkValidEnvironment(spark: Option[SparkSession], scopes: Seq[String], metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  20. def checkValidScope(scope: String): Unit
    Definition Classes
    CheckLicense
  21. def checkValidScopeAndEnvironment(scope: String, spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  22. def checkValidScopesAndEnvironment(scopes: Seq[String], spark: Option[SparkSession], checkLp: Boolean, metadata: Option[Map[String, Value]]): Unit
    Definition Classes
    CheckLicense
  23. val chunkWeight: FloatParam

    Relative weight of chunk embeddings in comparison to sentence embeddings.

    Relative weight of chunk embeddings in comparison to sentence embeddings. The value should between 0 and 1. The default is 0.5, which means the chunk and sentence embeddings are given equal weight.

  24. final def clear(param: Param[_]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    Params
  25. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  26. val configProtoBytes: IntArrayParam
    Definition Classes
    BertSentenceEmbeddings
  27. def copy(extra: ParamMap): BertSentenceEmbeddings
    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  28. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  29. def createDatabaseConnection(database: Name): RocksDBConnection
    Definition Classes
    HasStorageRef
  30. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  31. val dimension: ProtectedParam[Int]
    Definition Classes
    HasEmbeddingsProperties
  32. 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
  33. val engine: Param[String]
    Definition Classes
    HasEngine
  34. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  35. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  36. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  37. def explainParams(): String
    Definition Classes
    Params
  38. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  39. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  40. def extraValidateMsg: String
    Attributes
    protected
    Definition Classes
    RawAnnotator
  41. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  42. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  43. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  44. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  45. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  46. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  47. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  48. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  49. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  50. def getBatchSize: Int
    Definition Classes
    HasBatchedAnnotate
  51. def getCaseSensitive: Boolean
    Definition Classes
    HasCaseSensitiveProperties
  52. def getChunkWeight: Float

    Get the relative value of the chunk embeddings.

  53. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  54. def getConfigProtoBytes: Option[Array[Byte]]
    Definition Classes
    BertSentenceEmbeddings
  55. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  56. def getDimension: Int
    Definition Classes
    HasEmbeddingsProperties
  57. def getEngine: String
    Definition Classes
    HasEngine
  58. def getInputCols: Array[String]
    Definition Classes
    HasInputAnnotationCols
  59. def getIsLong: Boolean
    Definition Classes
    BertSentenceEmbeddings
  60. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  61. def getMaxSentenceLength: Int
    Definition Classes
    BertSentenceEmbeddings
  62. def getModelIfNotSet: Bert
    Definition Classes
    BertSentenceEmbeddings
  63. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  64. final def getOutputCol: String
    Definition Classes
    HasOutputAnnotationCol
  65. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  66. def getScopeWindow: (Int, Int)

    Get scopeWindow as a tuple of two Integers.

  67. def getSignatures: Option[Map[String, String]]
    Definition Classes
    BertSentenceEmbeddings
  68. def getStorageRef: String
    Definition Classes
    HasStorageRef
  69. def getStrategy: String
  70. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  71. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  72. def hasParent: Boolean
    Definition Classes
    Model
  73. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  74. val inExceptionMode: Boolean
    Attributes
    protected
    Definition Classes
    HasSafeBatchAnnotate
  75. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  76. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  77. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator types: DOCUMENT,CHUNK

    Input annotator types: DOCUMENT,CHUNK

    Definition Classes
    BertSentenceChunkEmbeddings → BertSentenceEmbeddings → HasInputAnnotationCols
  78. final val inputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  79. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  80. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  81. val isLong: ProtectedParam[Boolean]
    Definition Classes
    BertSentenceEmbeddings
  82. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  83. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  84. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  85. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  86. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  87. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  88. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  89. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  90. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  91. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  92. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  93. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  94. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  95. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  96. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  97. val maxSentenceLength: IntParam
    Definition Classes
    BertSentenceEmbeddings
  98. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  99. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  100. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  101. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  102. def onWrite(path: String, spark: SparkSession): Unit
    Definition Classes
    BertSentenceEmbeddings → ParamsAndFeaturesWritable
  103. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    BertSentenceChunkEmbeddings → HasInputAnnotationCols
  104. val outputAnnotatorType: AnnotatorType

    Output annotator types: CHUNK

    Output annotator types: CHUNK

    Definition Classes
    BertSentenceChunkEmbeddings → BertSentenceEmbeddings → HasOutputAnnotatorType
  105. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  106. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  107. var parent: Estimator[BertSentenceEmbeddings]
    Definition Classes
    Model
  108. def safeBatchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[Seq[Annotation]]
    Attributes
    protected
    Definition Classes
    HasSafeBatchAnnotate
  109. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  110. val scopeWindow: IntArrayParam
  111. def sentenceEndTokenId: Int
    Definition Classes
    BertSentenceEmbeddings
  112. def sentenceStartTokenId: Int
    Definition Classes
    BertSentenceEmbeddings
  113. def set[T](param: ProtectedParam[T], value: T): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasProtectedParams
  114. def set[T](feature: StructFeature[T], value: T): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  115. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  116. def set[T](feature: SetFeature[T], value: Set[T]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  117. def set[T](feature: ArrayFeature[T], value: Array[T]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  118. final def set(paramPair: ParamPair[_]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  119. final def set(param: String, value: Any): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  120. final def set[T](param: Param[T], value: T): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    Params
  121. def setBatchSize(size: Int): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasBatchedAnnotate
  122. def setCaseSensitive(value: Boolean): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings → HasCaseSensitiveProperties
  123. def setChunkWeight(value: Float): BertSentenceChunkEmbeddings.this.type

    Sets the wieght of the chunk embeddings relative to the sentence embeddings.

    Sets the wieght of the chunk embeddings relative to the sentence embeddings. The value should between 0 and 1.

  124. def setConfigProtoBytes(bytes: Array[Int]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  125. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  126. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  127. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  128. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  129. final def setDefault(paramPairs: ParamPair[_]*): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  130. final def setDefault[T](param: Param[T], value: T): BertSentenceChunkEmbeddings.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  131. def setDimension(value: Int): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings → HasEmbeddingsProperties
  132. def setDoExceptionHandling(value: Boolean): BertSentenceChunkEmbeddings.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
  133. def setExtraInputCols(value: Array[String]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasInputAnnotationCols
  134. final def setInputCols(value: String*): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasInputAnnotationCols
  135. def setInputCols(value: Array[String]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasInputAnnotationCols
  136. def setIsLong(value: Boolean): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  137. def setLazyAnnotator(value: Boolean): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    CanBeLazy
  138. def setMaxSentenceLength(value: Int): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  139. def setModelIfNotSet(spark: SparkSession, tensorflowWrapper: Option[TensorflowWrapper], onnxWrapper: Option[OnnxWrapper], openvinoWrapper: Option[OpenvinoWrapper]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  140. final def setOutputCol(value: String): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasOutputAnnotationCol
  141. def setParent(parent: Estimator[BertSentenceEmbeddings]): BertSentenceEmbeddings
    Definition Classes
    Model
  142. def setScopeWindow(window: (Int, Int)): BertSentenceChunkEmbeddings.this.type

    Set scope window to calculate scope embeddings.

    Set scope window to calculate scope embeddings. The scope window is defined by two non-negative integers. The default is (0, 0), which means only the chunk embeddings are used. The first integer defines the number of tokens before the chunk and the second integer defines the number of tokens after the chunk.

  143. def setSignatures(value: Map[String, String]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  144. def setStorageRef(value: String): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    HasStorageRef
  145. def setStrategy(value: String): BertSentenceChunkEmbeddings.this.type

    Sets the strategy for computing embeddings.

    Sets the strategy for computing embeddings. Supported strategies are: - "sentence_average": Average of sentence and chunk embeddings. - "scope_average": Average of scope and chunk embeddings. The scope is defined by the scope window. - "chunk_only": Only chunk embeddings are used. - "scope_only": Only scope embeddings are used. The scope is defined by the scope window. Note: If "scope_only" or "scope_average" strategy is used, the token column should be provided as input via setInputCols method. The scope text extraction is based on tokens and the scope window.

  146. def setVocabulary(value: Map[String, Int]): BertSentenceChunkEmbeddings.this.type
    Definition Classes
    BertSentenceEmbeddings
  147. val signatures: MapFeature[String, String]
    Definition Classes
    BertSentenceEmbeddings
  148. val storageRef: Param[String]
    Definition Classes
    HasStorageRef
  149. val strategy: Param[String]

    Strategy for computing embeddings.

    Strategy for computing embeddings. Supported strategies are: - "sentence_average": Average of sentence and chunk embeddings. - "scope_average": Average of scope and chunk embeddings. The scope is defined by the scope window. - "chunk_only": Only chunk embeddings are used. - "scope_only": Only scope embeddings are used. The scope is defined by the scope window. Note: If "scope_only" or "scope_average" strategy is used, the token column should be provided as input via setInputCols method. The scope text extraction is based on tokens and the scope window. Default is "sentence_average".

  150. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  151. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  152. def tokenize(sentences: Seq[Sentence]): Seq[WordpieceTokenizedSentence]
    Definition Classes
    BertSentenceEmbeddings
  153. final def transform(dataset: Dataset[_]): DataFrame
    Definition Classes
    AnnotatorModel → Transformer
  154. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  155. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  156. final def transformSchema(schema: StructType): StructType
    Definition Classes
    RawAnnotator → PipelineStage
  157. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  158. val uid: String
    Definition Classes
    BertSentenceChunkEmbeddings → BertSentenceEmbeddings → Identifiable
  159. def validate(schema: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  160. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
    Definition Classes
    HasStorageRef
  161. val vocabulary: MapFeature[String, Int]
    Definition Classes
    BertSentenceEmbeddings
  162. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  163. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  164. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  165. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  166. def wrapEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String]): Column
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  167. def wrapSentenceEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String]): Column
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  168. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  169. def writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOnnxModel
  170. def writeOnnxModels(path: String, spark: SparkSession, onnxWrappersWithNames: Seq[(OnnxWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOnnxModel
  171. def writeOpenvinoModel(path: String, spark: SparkSession, openvinoWrapper: OpenvinoWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOpenvinoModel
  172. def writeOpenvinoModels(path: String, spark: SparkSession, ovWrappersWithNames: Seq[(OpenvinoWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOpenvinoModel
  173. def writeTensorflowHub(path: String, tfPath: String, spark: SparkSession, suffix: String): Unit
    Definition Classes
    WriteTensorflowModel
  174. def writeTensorflowModel(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]]): Unit
    Definition Classes
    WriteTensorflowModel
  175. def writeTensorflowModelV2(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]], savedSignatures: Option[Map[String, String]]): Unit
    Definition Classes
    WriteTensorflowModel

Inherited from CheckLicense

Inherited from HasSafeBatchAnnotate[BertSentenceEmbeddings]

Inherited from HandleExceptionParams

Inherited from BertSentenceEmbeddings

Inherited from HasEngine

Inherited from HasCaseSensitiveProperties

Inherited from HasStorageRef

Inherited from HasEmbeddingsProperties

Inherited from HasProtectedParams

Inherited from WriteOnnxModel

Inherited from WriteOpenvinoModel

Inherited from WriteTensorflowModel

Inherited from HasBatchedAnnotate[BertSentenceEmbeddings]

Inherited from AnnotatorModel[BertSentenceEmbeddings]

Inherited from CanBeLazy

Inherited from RawAnnotator[BertSentenceEmbeddings]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[BertSentenceEmbeddings]

Inherited from Transformer

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

Inherited from Serializable

Inherited from Serializable

Inherited from Identifiable

Inherited from AnyRef

Inherited from Any

anno

getParam

param

setParam

Ungrouped