Class/Object

com.johnsnowlabs.nlp.embeddings

SentenceEmbeddings

Related Docs: object SentenceEmbeddings | package embeddings

Permalink

class SentenceEmbeddings extends AnnotatorModel[SentenceEmbeddings] with HasSimpleAnnotate[SentenceEmbeddings] with HasEmbeddingsProperties with HasStorageRef

Converts the results from WordEmbeddings, BertEmbeddings, or ElmoEmbeddings into sentence or document embeddings by either summing up or averaging all the word embeddings in a sentence or a document (depending on the inputCols).

This can be configured with setPoolingStrategy, which either be "AVERAGE" or "SUM".

For more extended examples see the Spark NLP Workshop. and the SentenceEmbeddingsTestSpec.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.embeddings.WordEmbeddingsModel
import com.johnsnowlabs.nlp.embeddings.SentenceEmbeddings
import com.johnsnowlabs.nlp.EmbeddingsFinisher
import org.apache.spark.ml.Pipeline

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

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

val embeddings = WordEmbeddingsModel.pretrained()
  .setInputCols("document", "token")
  .setOutputCol("embeddings")

val embeddingsSentence = new SentenceEmbeddings()
  .setInputCols(Array("document", "embeddings"))
  .setOutputCol("sentence_embeddings")
  .setPoolingStrategy("AVERAGE")

val embeddingsFinisher = new EmbeddingsFinisher()
  .setInputCols("sentence_embeddings")
  .setOutputCols("finished_embeddings")
  .setOutputAsVector(true)
  .setCleanAnnotations(false)

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    tokenizer,
    embeddings,
    embeddingsSentence,
    embeddingsFinisher
  ))

val data = Seq("This is a sentence.").toDF("text")
val result = pipeline.fit(data).transform(data)

result.selectExpr("explode(finished_embeddings) as result").show(5, 80)
+--------------------------------------------------------------------------------+
|                                                                          result|
+--------------------------------------------------------------------------------+
|[-0.22093398869037628,0.25130119919776917,0.41810303926467896,-0.380883991718...|
+--------------------------------------------------------------------------------+
Linear Supertypes
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. SentenceEmbeddings
  2. HasStorageRef
  3. HasEmbeddingsProperties
  4. HasSimpleAnnotate
  5. AnnotatorModel
  6. CanBeLazy
  7. RawAnnotator
  8. HasOutputAnnotationCol
  9. HasInputAnnotationCols
  10. HasOutputAnnotatorType
  11. ParamsAndFeaturesWritable
  12. HasFeatures
  13. DefaultParamsWritable
  14. MLWritable
  15. Model
  16. Transformer
  17. PipelineStage
  18. Logging
  19. Params
  20. Serializable
  21. Serializable
  22. Identifiable
  23. AnyRef
  24. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new SentenceEmbeddings()

    Permalink

    Internal constructor to submit a random UID

  2. new SentenceEmbeddings(uid: String)

    Permalink

Type Members

  1. type AnnotationContent = Seq[Row]

    Permalink

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    internal types to show Rows as a relevant StructType Should be deleted once Spark releases UserDefinedTypes to @developerAPI

    Attributes
    protected
    Definition Classes
    AnnotatorModel
  2. type AnnotatorType = String

    Permalink
    Definition Classes
    HasOutputAnnotatorType

Value Members

  1. final def !=(arg0: Any): Boolean

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  4. def $$[T](feature: StructFeature[T]): T

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  5. def $$[K, V](feature: MapFeature[K, V]): Map[K, V]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  6. def $$[T](feature: SetFeature[T]): Set[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  7. def $$[T](feature: ArrayFeature[T]): Array[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  8. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  9. def _transform(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): DataFrame

    Permalink
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  10. def afterAnnotate(dataset: DataFrame): DataFrame

    Permalink
    Attributes
    protected
    Definition Classes
    SentenceEmbeddingsAnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]

    Permalink

    takes a document and annotations and produces new annotations of this annotator's annotation type

    takes a document and annotations and produces new annotations of this annotator's annotation type

    annotations

    Annotations that correspond to inputAnnotationCols generated by previous annotators if any

    returns

    any number of annotations processed for every input annotation. Not necessary one to one relationship

    Definition Classes
    SentenceEmbeddingsHasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

    Permalink
    Attributes
    protected
    Definition Classes
    SentenceEmbeddingsAnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. final def clear(param: Param[_]): SentenceEmbeddings.this.type

    Permalink
    Definition Classes
    Params
  16. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  17. def copy(extra: ParamMap): SentenceEmbeddings

    Permalink

    requirement for annotators copies

    requirement for annotators copies

    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  18. def copyValues[T <: Params](to: T, extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  19. def createDatabaseConnection(database: Name): RocksDBConnection

    Permalink
    Definition Classes
    HasStorageRef
  20. final def defaultCopy[T <: Params](extra: ParamMap): T

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  21. def dfAnnotate: UserDefinedFunction

    Permalink

    Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column

    Wraps annotate to happen inside SparkSQL user defined functions in order to act with org.apache.spark.sql.Column

    returns

    udf function to be applied to inputCols using this annotator's annotate function as part of ML transformation

    Definition Classes
    HasSimpleAnnotate
  22. val dimension: IntParam

    Permalink

    Number of embedding dimensions (Default: 100)

    Number of embedding dimensions (Default: 100)

    Definition Classes
    SentenceEmbeddingsHasEmbeddingsProperties
  23. final def eq(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  24. def equals(arg0: Any): Boolean

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

    Permalink
    Definition Classes
    Params
  26. def explainParams(): String

    Permalink
    Definition Classes
    Params
  27. def extraValidate(structType: StructType): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  28. def extraValidateMsg: String

    Permalink

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  29. final def extractParamMap(): ParamMap

    Permalink
    Definition Classes
    Params
  30. final def extractParamMap(extra: ParamMap): ParamMap

    Permalink
    Definition Classes
    Params
  31. val features: ArrayBuffer[Feature[_, _, _]]

    Permalink
    Definition Classes
    HasFeatures
  32. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  33. def get[T](feature: StructFeature[T]): Option[T]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  34. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[T](feature: SetFeature[T]): Option[Set[T]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: ArrayFeature[T]): Option[Array[T]]

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. final def get[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params
  38. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  39. final def getDefault[T](param: Param[T]): Option[T]

    Permalink
    Definition Classes
    Params
  40. def getDimension: Int

    Permalink

    Number of embedding dimensions (Default: 100)

    Number of embedding dimensions (Default: 100)

    Definition Classes
    SentenceEmbeddingsHasEmbeddingsProperties
  41. def getInputCols: Array[String]

    Permalink

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  42. def getLazyAnnotator: Boolean

    Permalink
    Definition Classes
    CanBeLazy
  43. final def getOrDefault[T](param: Param[T]): T

    Permalink
    Definition Classes
    Params
  44. final def getOutputCol: String

    Permalink

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  45. def getParam(paramName: String): Param[Any]

    Permalink
    Definition Classes
    Params
  46. def getStorageRef: String

    Permalink
    Definition Classes
    HasStorageRef
  47. final def hasDefault[T](param: Param[T]): Boolean

    Permalink
    Definition Classes
    Params
  48. def hasParam(paramName: String): Boolean

    Permalink
    Definition Classes
    Params
  49. def hasParent: Boolean

    Permalink
    Definition Classes
    Model
  50. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  51. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  53. val inputAnnotatorTypes: Array[AnnotatorType]

    Permalink

    Input annotator type : DOCUMENT, WORD_EMBEDDINGS

    Input annotator type : DOCUMENT, WORD_EMBEDDINGS

    Definition Classes
    SentenceEmbeddingsHasInputAnnotationCols
  54. final val inputCols: StringArrayParam

    Permalink

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

    columns that contain annotations necessary to run this annotator AnnotatorType is used both as input and output columns if not specified

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

    Permalink
    Definition Classes
    Params
  56. final def isInstanceOf[T0]: Boolean

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

    Permalink
    Definition Classes
    Params
  58. def isTraceEnabled(): Boolean

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  59. val lazyAnnotator: BooleanParam

    Permalink
    Definition Classes
    CanBeLazy
  60. def log: Logger

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

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

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  67. def logName: String

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

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

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

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

    Permalink
    Attributes
    protected
    Definition Classes
    Logging
  72. def msgHelper(schema: StructType): String

    Permalink
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  73. final def ne(arg0: AnyRef): Boolean

    Permalink
    Definition Classes
    AnyRef
  74. final def notify(): Unit

    Permalink
    Definition Classes
    AnyRef
  75. final def notifyAll(): Unit

    Permalink
    Definition Classes
    AnyRef
  76. def onWrite(path: String, spark: SparkSession): Unit

    Permalink
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  77. val outputAnnotatorType: AnnotatorType

    Permalink

    Output annotator type : SENTENCE_EMBEDDINGS

    Output annotator type : SENTENCE_EMBEDDINGS

    Definition Classes
    SentenceEmbeddingsHasOutputAnnotatorType
  78. final val outputCol: Param[String]

    Permalink
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  79. lazy val params: Array[Param[_]]

    Permalink
    Definition Classes
    Params
  80. var parent: Estimator[SentenceEmbeddings]

    Permalink
    Definition Classes
    Model
  81. val poolingStrategy: Param[String]

    Permalink

    Choose how you would like to aggregate Word Embeddings to Sentence Embeddings (Default: "AVERAGE").

    Choose how you would like to aggregate Word Embeddings to Sentence Embeddings (Default: "AVERAGE"). Can either be "AVERAGE" or "SUM".

  82. def save(path: String): Unit

    Permalink
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  83. def set[T](feature: StructFeature[T], value: T): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  84. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  85. def set[T](feature: SetFeature[T], value: Set[T]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  86. def set[T](feature: ArrayFeature[T], value: Array[T]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  87. final def set(paramPair: ParamPair[_]): SentenceEmbeddings.this.type

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

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

    Permalink
    Definition Classes
    Params
  90. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  91. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): SentenceEmbeddings.this.type

    Permalink
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. final def setDefault(paramPairs: ParamPair[_]*): SentenceEmbeddings.this.type

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

    Permalink
    Attributes
    protected
    Definition Classes
    Params
  96. def setDimension(value: Int): SentenceEmbeddings.this.type

    Permalink

    Definition Classes
    HasEmbeddingsProperties
  97. final def setInputCols(value: String*): SentenceEmbeddings.this.type

    Permalink
    Definition Classes
    HasInputAnnotationCols
  98. final def setInputCols(value: Array[String]): SentenceEmbeddings.this.type

    Permalink

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  99. def setLazyAnnotator(value: Boolean): SentenceEmbeddings.this.type

    Permalink
    Definition Classes
    CanBeLazy
  100. final def setOutputCol(value: String): SentenceEmbeddings.this.type

    Permalink

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  101. def setParent(parent: Estimator[SentenceEmbeddings]): SentenceEmbeddings

    Permalink
    Definition Classes
    Model
  102. def setPoolingStrategy(strategy: String): SentenceEmbeddings.this.type

    Permalink

    Choose how you would like to aggregate Word Embeddings to Sentence Embeddings (Default: "AVERAGE").

    Choose how you would like to aggregate Word Embeddings to Sentence Embeddings (Default: "AVERAGE"). Can either be "AVERAGE" or "SUM".

  103. def setStorageRef(value: String): SentenceEmbeddings.this.type

    Permalink
    Definition Classes
    HasStorageRef
  104. val storageRef: Param[String]

    Permalink

    Unique identifier for storage (Default: this.uid)

    Unique identifier for storage (Default: this.uid)

    Definition Classes
    HasStorageRef
  105. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  106. def toString(): String

    Permalink
    Definition Classes
    Identifiable → AnyRef → Any
  107. final def transform(dataset: Dataset[_]): DataFrame

    Permalink

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    Given requirements are met, this applies ML transformation within a Pipeline or stand-alone Output annotation will be generated as a new column, previous annotations are still available separately metadata is built at schema level to record annotations structural information outside its content

    dataset

    Dataset[Row]

    Definition Classes
    AnnotatorModel → Transformer
  108. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  109. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame

    Permalink
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  110. final def transformSchema(schema: StructType): StructType

    Permalink

    requirement for pipeline transformation validation.

    requirement for pipeline transformation validation. It is called on fit()

    Definition Classes
    RawAnnotator → PipelineStage
  111. def transformSchema(schema: StructType, logging: Boolean): StructType

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

    Permalink
    Definition Classes
    SentenceEmbeddings → Identifiable
  113. def validate(schema: StructType): Boolean

    Permalink

    takes a Dataset and checks to see if all the required annotation types are present.

    takes a Dataset and checks to see if all the required annotation types are present.

    schema

    to be validated

    returns

    True if all the required types are present, else false

    Attributes
    protected
    Definition Classes
    RawAnnotator
  114. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit

    Permalink
    Definition Classes
    HasStorageRef
  115. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  118. def wrapColumnMetadata(col: Column): Column

    Permalink
    Attributes
    protected
    Definition Classes
    RawAnnotator
  119. def wrapEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String] = None): Column

    Permalink
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  120. def wrapSentenceEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String] = None): Column

    Permalink
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  121. def write: MLWriter

    Permalink
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasStorageRef

Inherited from HasEmbeddingsProperties

Inherited from CanBeLazy

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[SentenceEmbeddings]

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

Parameters

A list of (hyper-)parameter keys this annotator can take. Users can set and get the parameter values through setters and getters, respectively.

Annotator types

Required input and expected output annotator types

Members

Parameter setters

Parameter getters