Packages

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

Produces contextual chunk-level embeddings using the Late Chunking technique described in Jin et al. (2024).

Unlike ChunkEmbeddings, which embeds each chunk in isolation, LateChunkEmbeddings expects that the upstream token-embedding stage (e.g. ModernBertEmbeddings or LongformerEmbeddings) has already processed the **full document** in a single forward pass, producing contextual token representations. This annotator then locates the tokens that fall within each chunk's character span and mean-pools them into a single SENTENCE_EMBEDDINGS vector — so every chunk embedding is informed by the complete document context rather than being isolated. By default, token selection is sentence-aware: selected token embeddings must fall inside the chunk span and have the same sentence id as the chunk. Set sentenceAwareFiltering to false to use span-only filtering.

Ordering requirement

LateChunkEmbeddings must appear after the token-embedding stage in the pipeline. Placing it before the embedding stage will raise a runtime error.

Context-window limitation

The contextual benefit is bounded by the upstream model's maximum sequence length (e.g. 8 192 tokens for ModernBertEmbeddings). Documents that exceed this limit are truncated before embedding, reducing cross-chunk context for tokens near the end of very long documents.

Warning: upstream model must process the full document

The upstream embedding stage must use DOCUMENT (not SENTENCE) as its input annotation type, processing the entire document in a single forward pass. If a SentenceDetector is placed before the embedding model, each sentence is embedded independently and the contextual benefit of late chunking is lost — the annotator will still run without error but will produce embeddings equivalent to naive ChunkEmbeddings.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.{DocumentAssembler, Doc2Chunk}
import com.johnsnowlabs.nlp.annotators.Tokenizer
import com.johnsnowlabs.nlp.embeddings.{ModernBertEmbeddings, LateChunkEmbeddings}
import org.apache.spark.ml.Pipeline

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

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

val tokenEmbeddings = ModernBertEmbeddings.pretrained("modernbert-base", "en")
  .setInputCols("document", "token")
  .setOutputCol("token_embeddings")
  .setMaxSentenceLength(8192)

val chunker = new Doc2Chunk()
  .setInputCols(Array("document"))
  .setChunkCol("chunks")
  .setIsArray(true)
  .setOutputCol("chunk")

val lateChunkEmbeddings = new LateChunkEmbeddings()
  .setInputCols("document", "chunk", "token_embeddings")
  .setOutputCol("late_chunk_embeddings")
  .setPoolingStrategy("AVERAGE")

val pipeline = new Pipeline()
  .setStages(Array(
    documentAssembler,
    tokenizer,
    tokenEmbeddings,
    chunker,
    lateChunkEmbeddings
  ))

val data = Seq((
  "AcmeDrug was prescribed for migraine in March. The patient took two doses.\n\n" +
  "It caused severe nausea the next day, and therapy was stopped.",
  Array(
    "AcmeDrug was prescribed for migraine in March. The patient took two doses.",
    "It caused severe nausea the next day, and therapy was stopped.")
)).toDF("text", "chunks")

val result = pipeline.fit(data).transform(data)

result.selectExpr("explode(late_chunk_embeddings) as r")
  .select("r.annotatorType", "r.result", "r.embeddings")
  .show(5, 80)
// +-------------------+--------------------------------------------------------------------------+--------------------------------------------------------------------------------+
// |      annotatorType|                                                                    result|                                                                      embeddings|
// +-------------------+--------------------------------------------------------------------------+--------------------------------------------------------------------------------+
// |sentence_embeddings|AcmeDrug was prescribed for migraine in March. The patient took two doses.|[0.050471008, -0.07595207, 0.031268876, 0.15105441, -0.013697156, 0.08131724,...|
// |sentence_embeddings|            It caused severe nausea the next day, and therapy was stopped.|[0.0735685, 0.0060829176, 0.12051964, 0.22399232, 0.055884164, 0.066795066, 0...|
// +-------------------+--------------------------------------------------------------------------+--------------------------------------------------------------------------------+
Linear Supertypes
HasStorageRef, HasEmbeddingsProperties, HasProtectedParams, HasSimpleAnnotate[LateChunkEmbeddings], AnnotatorModel[LateChunkEmbeddings], CanBeLazy, RawAnnotator[LateChunkEmbeddings], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[LateChunkEmbeddings], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. LateChunkEmbeddings
  2. HasStorageRef
  3. HasEmbeddingsProperties
  4. HasProtectedParams
  5. HasSimpleAnnotate
  6. AnnotatorModel
  7. CanBeLazy
  8. RawAnnotator
  9. HasOutputAnnotationCol
  10. HasInputAnnotationCols
  11. HasOutputAnnotatorType
  12. ParamsAndFeaturesWritable
  13. HasFeatures
  14. DefaultParamsWritable
  15. MLWritable
  16. Model
  17. Transformer
  18. PipelineStage
  19. Logging
  20. Params
  21. Serializable
  22. Serializable
  23. Identifiable
  24. AnyRef
  25. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new LateChunkEmbeddings()

    Internal constructor to submit a random UID

  2. new LateChunkEmbeddings(uid: String)

Type Members

  1. implicit class ProtectedParam[T] extends Param[T]
    Definition Classes
    HasProtectedParams
  2. type AnnotationContent = Seq[Row]

    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
  3. type AnnotatorType = String
    Definition Classes
    HasOutputAnnotatorType

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

    Attaches Spark column metadata that marks the output as SENTENCE_EMBEDDINGS with the correct dimension and storage reference — enabling downstream use with EmbeddingsFinisher or sentence-level classifiers.

    Attaches Spark column metadata that marks the output as SENTENCE_EMBEDDINGS with the correct dimension and storage reference — enabling downstream use with EmbeddingsFinisher or sentence-level classifiers.

    Attributes
    protected
    Definition Classes
    LateChunkEmbeddings → AnnotatorModel
  11. def annotate(annotations: Seq[Annotation]): Seq[Annotation]

    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.

    The method:

    1. Collects all contextual token embeddings produced by the upstream model across the entire document (flattened across all internal sentence buckets). 2. For each CHUNK annotation, selects the token embeddings whose character offsets fall within the chunk's [begin, end] span. 3. Mean-pools the selected embeddings into a single vector. 4. Emits one SENTENCE_EMBEDDINGS annotation per chunk, preserving the chunk's text, offsets, and metadata.
    annotations

    Annotations from all configured input columns (DOCUMENT, CHUNK, WORD_EMBEDDINGS).

    returns

    One SENTENCE_EMBEDDINGS annotation per chunk that has at least one overlapping token embedding. Chunks with no matching tokens are silently dropped.

    Definition Classes
    LateChunkEmbeddings → HasSimpleAnnotate
  12. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  13. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]

    Reads the storage reference and embedding dimension from the upstream WORD_EMBEDDINGS column metadata before any executor UDF runs.

    Reads the storage reference and embedding dimension from the upstream WORD_EMBEDDINGS column metadata before any executor UDF runs.

    Why dimension is set here, not inside annotate()

    AnnotatorModel._transform calls beforeAnnotate eagerly on the driver, then builds a lazy withColumn(...udf...) plan, then calls afterAnnotate — also on the driver — before any executor has executed the UDF. This means setDimension() called inside annotate() (executor context) would happen after afterAnnotate has already baked the dimension into the output column metadata. By reading the dimension from the Spark schema field metadata here (set by the upstream model's own afterAnnotate), we guarantee $(dimension) is correct when afterAnnotate calls wrapSentenceEmbeddingsMetadata.

    Attributes
    protected
    Definition Classes
    LateChunkEmbeddings → AnnotatorModel
  14. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  15. final def clear(param: Param[_]): LateChunkEmbeddings.this.type
    Definition Classes
    Params
  16. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  17. def copy(extra: ParamMap): LateChunkEmbeddings

    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
    Attributes
    protected
    Definition Classes
    Params
  19. def createDatabaseConnection(database: Name): RocksDBConnection
    Definition Classes
    HasStorageRef
  20. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  21. def dfAnnotate: UserDefinedFunction

    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: ProtectedParam[Int]

    Number of embedding dimensions.

    Number of embedding dimensions. Inferred automatically from the upstream token embeddings on the first annotation.

    Definition Classes
    LateChunkEmbeddings → HasEmbeddingsProperties
  23. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  24. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  25. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  26. def explainParams(): String
    Definition Classes
    Params
  27. final val extraInputCols: StringArrayParam
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  28. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  29. def extraValidateMsg: String

    Override for additional custom schema checks

    Override for additional custom schema checks

    Attributes
    protected
    Definition Classes
    RawAnnotator
  30. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  31. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  32. val features: ArrayBuffer[Feature[_, _, _]]
    Definition Classes
    HasFeatures
  33. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  34. def get[T](feature: StructFeature[T]): Option[T]
    Attributes
    protected
    Definition Classes
    HasFeatures
  35. def get[K, V](feature: MapFeature[K, V]): Option[Map[K, V]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  36. def get[T](feature: SetFeature[T]): Option[Set[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  37. def get[T](feature: ArrayFeature[T]): Option[Array[T]]
    Attributes
    protected
    Definition Classes
    HasFeatures
  38. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  39. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  40. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  41. def getDimension: Int

    Number of embedding dimensions

    Number of embedding dimensions

    Definition Classes
    LateChunkEmbeddings → HasEmbeddingsProperties
  42. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  43. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  44. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  45. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  46. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  47. def getPoolingStrategy: String

    Returns the current pooling strategy.

  48. def getSentenceAwareFiltering: Boolean

    Returns whether token filtering requires matching sentence id.

  49. def getSkipOOV: Boolean

    Returns whether OOV token embeddings are skipped during pooling.

  50. def getStorageRef: String
    Definition Classes
    HasStorageRef
  51. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  52. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  53. def hasParent: Boolean
    Definition Classes
    Model
  54. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  55. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  56. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  57. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator types : DOCUMENT, CHUNK, WORD_EMBEDDINGS

    Input annotator types : DOCUMENT, CHUNK, WORD_EMBEDDINGS

    Definition Classes
    LateChunkEmbeddings → HasInputAnnotationCols
  58. final val inputCols: StringArrayParam

    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
  59. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  60. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  61. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  62. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  63. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  64. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  65. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  70. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  72. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  76. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  77. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  78. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  79. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  80. def onWrite(path: String, spark: SparkSession): Unit
    Attributes
    protected
    Definition Classes
    ParamsAndFeaturesWritable
  81. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  82. val outputAnnotatorType: AnnotatorType

    Output annotator type : SENTENCE_EMBEDDINGS

    Output annotator type : SENTENCE_EMBEDDINGS

    Definition Classes
    LateChunkEmbeddings → HasOutputAnnotatorType
  83. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  84. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  85. var parent: Estimator[LateChunkEmbeddings]
    Definition Classes
    Model
  86. val poolingStrategy: Param[String]

    Strategy used to aggregate token embeddings within each chunk span.

    Strategy used to aggregate token embeddings within each chunk span. Either "AVERAGE" (default) or "SUM".

  87. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  88. val sentenceAwareFiltering: BooleanParam

    Whether to restrict token embeddings to the same sentence as the chunk when pooling (Default: true).

    Whether to restrict token embeddings to the same sentence as the chunk when pooling (Default: true). When true, selected token embeddings must both fall inside the chunk span and have the same sentence id as the chunk.

  89. def set[T](param: ProtectedParam[T], value: T): LateChunkEmbeddings.this.type

    Sets the value for a protected Param.

    Sets the value for a protected Param.

    If the parameter was already set, it will not be set again. Default values do not count as a set value and can be overridden.

    T

    Type of the parameter

    param

    Protected parameter to set

    value

    Value for the parameter

    returns

    This object

    Definition Classes
    HasProtectedParams
  90. def set[T](feature: StructFeature[T], value: T): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  91. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  92. def set[T](feature: SetFeature[T], value: Set[T]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  93. def set[T](feature: ArrayFeature[T], value: Array[T]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  94. final def set(paramPair: ParamPair[_]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  95. final def set(param: String, value: Any): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  96. final def set[T](param: Param[T], value: T): LateChunkEmbeddings.this.type
    Definition Classes
    Params
  97. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  98. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  99. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  100. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  101. final def setDefault(paramPairs: ParamPair[_]*): LateChunkEmbeddings.this.type
    Attributes
    protected
    Definition Classes
    Params
  102. final def setDefault[T](param: Param[T], value: T): LateChunkEmbeddings.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  103. def setDimension(value: Int): LateChunkEmbeddings.this.type

    Definition Classes
    HasEmbeddingsProperties
  104. def setExtraInputCols(value: Array[String]): LateChunkEmbeddings.this.type
    Definition Classes
    HasInputAnnotationCols
  105. final def setInputCols(value: String*): LateChunkEmbeddings.this.type
    Definition Classes
    HasInputAnnotationCols
  106. def setInputCols(value: Array[String]): LateChunkEmbeddings.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  107. def setLazyAnnotator(value: Boolean): LateChunkEmbeddings.this.type
    Definition Classes
    CanBeLazy
  108. final def setOutputCol(value: String): LateChunkEmbeddings.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  109. def setParent(parent: Estimator[LateChunkEmbeddings]): LateChunkEmbeddings
    Definition Classes
    Model
  110. def setPoolingStrategy(strategy: String): LateChunkEmbeddings.this.type

    Sets pooling strategy.

    Sets pooling strategy. Must be "AVERAGE" or "SUM".

  111. def setSentenceAwareFiltering(value: Boolean): LateChunkEmbeddings.this.type

    Sets whether token filtering should also require matching sentence id.

  112. def setSkipOOV(value: Boolean): LateChunkEmbeddings.this.type

    Sets whether to skip OOV token embeddings during pooling.

  113. def setStorageRef(value: String): LateChunkEmbeddings.this.type
    Definition Classes
    HasStorageRef
  114. val skipOOV: BooleanParam

    Whether to skip OOV (out-of-vocabulary) token embeddings when pooling (Default: true).

    Whether to skip OOV (out-of-vocabulary) token embeddings when pooling (Default: true). When true, default zero-vectors for OOV tokens are excluded from the pool.

  115. val storageRef: Param[String]

    Unique identifier for storage (Default: this.uid)

    Unique identifier for storage (Default: this.uid)

    Definition Classes
    HasStorageRef
  116. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  117. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  118. final def transform(dataset: Dataset[_]): DataFrame

    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
  119. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  120. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  121. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

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

    Definition Classes
    RawAnnotator → PipelineStage
  122. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  123. val uid: String
    Definition Classes
    LateChunkEmbeddings → Identifiable
  124. def validate(schema: StructType): Boolean

    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
  125. def validateStorageRef(dataset: Dataset[_], inputCols: Array[String], annotatorType: String): Unit
    Definition Classes
    HasStorageRef
  126. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  127. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  128. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  129. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  130. def wrapEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String] = None): Column
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  131. def wrapSentenceEmbeddingsMetadata(col: Column, embeddingsDim: Int, embeddingsRef: Option[String] = None): Column
    Attributes
    protected
    Definition Classes
    HasEmbeddingsProperties
  132. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable

Inherited from HasStorageRef

Inherited from HasEmbeddingsProperties

Inherited from HasProtectedParams

Inherited from HasSimpleAnnotate[LateChunkEmbeddings]

Inherited from AnnotatorModel[LateChunkEmbeddings]

Inherited from CanBeLazy

Inherited from RawAnnotator[LateChunkEmbeddings]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[LateChunkEmbeddings]

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