Packages

class BartTransformer extends AnnotatorModel[BartTransformer] with HasBatchedAnnotate[BartTransformer] with ParamsAndFeaturesWritable with WriteTensorflowModel with WriteOnnxModel with HasEngine with HasGeneratorProperties

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension Transformer

The Facebook BART (Bidirectional and Auto-Regressive Transformer) model is a state-of-the-art language generation model that was introduced by Facebook AI in 2019. It is based on the transformer architecture and is designed to handle a wide range of natural language processing tasks such as text generation, summarization, and machine translation.

BART is unique in that it is both bidirectional and auto-regressive, meaning that it can generate text both from left-to-right and from right-to-left. This allows it to capture contextual information from both past and future tokens in a sentence,resulting in more accurate and natural language generation.

The model was trained on a large corpus of text data using a combination of unsupervised and supervised learning techniques. It incorporates pretraining and fine-tuning phases, where the model is first trained on a large unlabeled corpus of text, and then fine-tuned on specific downstream tasks.

BART has achieved state-of-the-art performance on a wide range of NLP tasks, including summarization, question-answering, and language translation. Its ability to handle multiple tasks and its high performance on each of these tasks make it a versatile and valuable tool for natural language processing applications.

Pretrained models can be loaded with pretrained of the companion object:

val bart = BartTransformer.pretrained()
  .setInputCols("document")
  .setOutputCol("generation")

The default model is "distilbart_xsum_12_6", if no name is provided. For available pretrained models please see the Models Hub.

For extended examples of usage, see BartTestSpec.

References:

Paper Abstract:

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Tranformer-based neural machine translation architecture which, despite its simplicity, can be seen as generalizing BERT (due to the bidirectional encoder), GPT (with the left-to-right decoder), and other recent pretraining schemes. We evaluate a number of noising approaches, finding the best performance by both randomly shuffling the order of sentences and using a novel in-filling scheme, where spans of text are replaced with a single mask token. BART is particularly effective when fine tuned for text generation but also works well for comprehension tasks. It matches the performance of RoBERTa on GLUE and SQuAD, and achieves new stateof-the-art results on a range of abstractive dialogue, question answering, and summarization tasks, with gains of up to 3.5 ROUGE. BART also provides a 1.1 BLEU increase over a back-translation system for machine translation, with only target language pretraining. We also replicate other pretraining schemes within the BART framework, to understand their effect on end-task performance

Note:

This is a very computationally expensive module especially on larger sequence. The use of an accelerator such as GPU is recommended.

Example

import spark.implicits._
import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.seq2seq.GPT2Transformer
import org.apache.spark.ml.Pipeline

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

val bart = BartTransformer.pretrained("distilbart_xsum_12_6")
  .setInputCols(Array("documents"))
  .setMinOutputLength(10)
  .setMaxOutputLength(30)
  .setDoSample(true)
  .setTopK(50)
  .setOutputCol("generation")

val pipeline = new Pipeline().setStages(Array(documentAssembler, bart))

val data = Seq(
  "PG&E stated it scheduled the blackouts in response to forecasts for high winds " +
  "amid dry conditions. The aim is to reduce the risk of wildfires. Nearly 800 thousand customers were " +
  "scheduled to be affected by the shutoffs which were expected to last through at least midday tomorrow."
).toDF("text")
val result = pipeline.fit(data).transform(data)

results.select("generation.result").show(truncate = false)
+--------------------------------------------------------------+
|result                                                        |
+--------------------------------------------------------------+
|[Nearly 800 thousand customers were affected by the shutoffs.]|
+--------------------------------------------------------------+
Linear Supertypes
HasGeneratorProperties, HasEngine, WriteOnnxModel, WriteTensorflowModel, HasBatchedAnnotate[BartTransformer], AnnotatorModel[BartTransformer], CanBeLazy, RawAnnotator[BartTransformer], HasOutputAnnotationCol, HasInputAnnotationCols, HasOutputAnnotatorType, ParamsAndFeaturesWritable, HasFeatures, DefaultParamsWritable, MLWritable, Model[BartTransformer], Transformer, PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. BartTransformer
  2. HasGeneratorProperties
  3. HasEngine
  4. WriteOnnxModel
  5. WriteTensorflowModel
  6. HasBatchedAnnotate
  7. AnnotatorModel
  8. CanBeLazy
  9. RawAnnotator
  10. HasOutputAnnotationCol
  11. HasInputAnnotationCols
  12. HasOutputAnnotatorType
  13. ParamsAndFeaturesWritable
  14. HasFeatures
  15. DefaultParamsWritable
  16. MLWritable
  17. Model
  18. Transformer
  19. PipelineStage
  20. Logging
  21. Params
  22. Serializable
  23. Serializable
  24. Identifiable
  25. AnyRef
  26. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

    uid

    required uid for storing annotator to disk

Type Members

  1. 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
  2. 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
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  11. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  12. def batchAnnotate(batchedAnnotations: Seq[Array[Annotation]]): Seq[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

    batchedAnnotations

    Annotations in batches that correspond to inputAnnotationCols generated by previous annotators if any

    returns

    any number of annotations processed for every batch of input annotations. Not necessary one to one relationship IMPORTANT: !MUST! return sequences of equal lengths !! IMPORTANT: !MUST! return sentences that belong to the same original row !! (challenging)

    Definition Classes
    BartTransformer → HasBatchedAnnotate
  13. def batchProcess(rows: Iterator[_]): Iterator[Row]
    Definition Classes
    HasBatchedAnnotate
  14. val batchSize: IntParam

    Size of every batch (Default depends on model).

    Size of every batch (Default depends on model).

    Definition Classes
    HasBatchedAnnotate
  15. val beamSize: IntParam

    Beam size for the beam search algorithm (Default: 4)

    Beam size for the beam search algorithm (Default: 4)

    Definition Classes
    HasGeneratorProperties
  16. def beforeAnnotate(dataset: Dataset[_]): Dataset[_]
    Attributes
    protected
    Definition Classes
    AnnotatorModel
  17. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  18. final def clear(param: Param[_]): BartTransformer.this.type
    Definition Classes
    Params
  19. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  20. val configProtoBytes: IntArrayParam

    ConfigProto from tensorflow, serialized into byte array.

    ConfigProto from tensorflow, serialized into byte array. Get with config_proto.SerializeToString()

  21. def copy(extra: ParamMap): BartTransformer

    requirement for annotators copies

    requirement for annotators copies

    Definition Classes
    RawAnnotator → Model → Transformer → PipelineStage → Params
  22. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  23. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  24. val doSample: BooleanParam

    Whether or not to use sampling, use greedy decoding otherwise (Default: false)

    Whether or not to use sampling, use greedy decoding otherwise (Default: false)

    Definition Classes
    HasGeneratorProperties
  25. val engine: Param[String]

    This param is set internally once via loadSavedModel.

    This param is set internally once via loadSavedModel. That's why there is no setter

    Definition Classes
    HasEngine
  26. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  27. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  28. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  29. def explainParams(): String
    Definition Classes
    Params
  30. def extraValidate(structType: StructType): Boolean
    Attributes
    protected
    Definition Classes
    RawAnnotator
  31. def extraValidateMsg: String

    Override for additional custom schema checks

    Override for additional custom schema checks

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

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotate
  42. def getBeamSize: Int

    Definition Classes
    HasGeneratorProperties
  43. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  44. def getConfigProtoBytes: Option[Array[Byte]]

  45. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  46. def getDoSample: Boolean

    Definition Classes
    HasGeneratorProperties
  47. def getEngine: String

    Definition Classes
    HasEngine
  48. def getIgnoreTokenIds: Array[Int]

  49. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  50. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  51. def getMaxOutputLength: Int

    Definition Classes
    HasGeneratorProperties
  52. def getMinOutputLength: Int

    Definition Classes
    HasGeneratorProperties
  53. def getModelIfNotSet: Bart

  54. def getNReturnSequences: Int

    Definition Classes
    HasGeneratorProperties
  55. def getNoRepeatNgramSize: Int

    Definition Classes
    HasGeneratorProperties
  56. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  57. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  58. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  59. def getRandomSeed: Option[Long]

    Definition Classes
    HasGeneratorProperties
  60. def getRepetitionPenalty: Double

    Definition Classes
    HasGeneratorProperties
  61. def getSignatures: Option[Map[String, String]]

  62. def getStopTokenIds: Array[Int]

    Definition Classes
    HasGeneratorProperties
  63. def getTask: Option[String]

    Definition Classes
    HasGeneratorProperties
  64. def getTemperature: Double

    Definition Classes
    HasGeneratorProperties
  65. def getTopK: Int

    Definition Classes
    HasGeneratorProperties
  66. def getTopP: Double

    Definition Classes
    HasGeneratorProperties
  67. def getUseCache: Boolean
  68. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  69. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  70. def hasParent: Boolean
    Definition Classes
    Model
  71. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  72. var ignoreTokenIds: IntArrayParam

    A list of token ids which are ignored in the decoder 's output (Default: Array())

  73. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  74. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  75. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator type : DOCUMENT

    Input annotator type : DOCUMENT

    Definition Classes
    BartTransformer → HasInputAnnotationCols
  76. 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
  77. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  78. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  79. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  80. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  81. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  82. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  83. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  84. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  85. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  86. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  87. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  88. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  89. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  90. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  91. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  92. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  93. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  94. val maxInputLength: IntParam

    max length of the input sequence (Default: 0)

    max length of the input sequence (Default: 0)

    Definition Classes
    HasGeneratorProperties
  95. val maxOutputLength: IntParam

    Maximum length of the sequence to be generated (Default: 20)

    Maximum length of the sequence to be generated (Default: 20)

    Definition Classes
    HasGeneratorProperties
  96. val merges: MapFeature[(String, String), Int]

    Holding merges.txt coming from RoBERTa model

  97. val minOutputLength: IntParam

    Minimum length of the sequence to be generated (Default: 0)

    Minimum length of the sequence to be generated (Default: 0)

    Definition Classes
    HasGeneratorProperties
  98. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  99. val nReturnSequences: IntParam

    The number of sequences to return from the beam search.

    The number of sequences to return from the beam search.

    Definition Classes
    HasGeneratorProperties
  100. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  101. val noRepeatNgramSize: IntParam

    If set to int > 0, all ngrams of that size can only occur once (Default: 0)

    If set to int > 0, all ngrams of that size can only occur once (Default: 0)

    Definition Classes
    HasGeneratorProperties
  102. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  103. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  104. def onWrite(path: String, spark: SparkSession): Unit
    Definition Classes
    BartTransformer → ParamsAndFeaturesWritable
  105. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  106. val outputAnnotatorType: String

    Output annotator type : DOCUMENT

    Output annotator type : DOCUMENT

    Definition Classes
    BartTransformer → HasOutputAnnotatorType
  107. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  108. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  109. var parent: Estimator[BartTransformer]
    Definition Classes
    Model
  110. val randomSeed: Option[Long]

    Optional Random seed for the model.

    Optional Random seed for the model. Needs to be of type Int.

    Definition Classes
    HasGeneratorProperties
  111. val repetitionPenalty: DoubleParam

    The parameter for repetition penalty (Default: 1.0).

    The parameter for repetition penalty (Default: 1.0). 1.0 means no penalty. See this paper for more details.

    Definition Classes
    HasGeneratorProperties
  112. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  113. def set[T](feature: StructFeature[T], value: T): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  114. def set[K, V](feature: MapFeature[K, V], value: Map[K, V]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  115. def set[T](feature: SetFeature[T], value: Set[T]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  116. def set[T](feature: ArrayFeature[T], value: Array[T]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  117. final def set(paramPair: ParamPair[_]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  118. final def set(param: String, value: Any): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  119. final def set[T](param: Param[T], value: T): BartTransformer.this.type
    Definition Classes
    Params
  120. def setBatchSize(size: Int): BartTransformer.this.type

    Size of every batch.

    Size of every batch.

    Definition Classes
    HasBatchedAnnotate
  121. def setBeamSize(beamNum: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  122. def setConfigProtoBytes(bytes: Array[Int]): BartTransformer.this.type

  123. def setDefault[T](feature: StructFeature[T], value: () ⇒ T): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  124. def setDefault[K, V](feature: MapFeature[K, V], value: () ⇒ Map[K, V]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  125. def setDefault[T](feature: SetFeature[T], value: () ⇒ Set[T]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  126. def setDefault[T](feature: ArrayFeature[T], value: () ⇒ Array[T]): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    HasFeatures
  127. final def setDefault(paramPairs: ParamPair[_]*): BartTransformer.this.type
    Attributes
    protected
    Definition Classes
    Params
  128. final def setDefault[T](param: Param[T], value: T): BartTransformer.this.type
    Attributes
    protected[org.apache.spark.ml]
    Definition Classes
    Params
  129. def setDoSample(value: Boolean): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  130. def setIgnoreTokenIds(tokenIds: Array[Int]): BartTransformer.this.type

  131. final def setInputCols(value: String*): BartTransformer.this.type
    Definition Classes
    HasInputAnnotationCols
  132. def setInputCols(value: Array[String]): BartTransformer.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  133. def setLazyAnnotator(value: Boolean): BartTransformer.this.type
    Definition Classes
    CanBeLazy
  134. def setMaxInputLength(value: Int): BartTransformer.this.type
    Definition Classes
    HasGeneratorProperties
  135. def setMaxOutputLength(value: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  136. def setMerges(value: Map[(String, String), Int]): BartTransformer.this.type

  137. def setMinOutputLength(value: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  138. def setModelIfNotSet(spark: SparkSession, tfWrapper: Option[TensorflowWrapper], onnxWrappers: Option[EncoderDecoderWithoutPastWrappers], useCache: Boolean): BartTransformer.this.type

  139. def setNReturnSequences(beamNum: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  140. def setNoRepeatNgramSize(value: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  141. final def setOutputCol(value: String): BartTransformer.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  142. def setParent(parent: Estimator[BartTransformer]): BartTransformer
    Definition Classes
    Model
  143. def setRandomSeed(value: Long): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  144. def setRepetitionPenalty(value: Double): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  145. def setSignatures(value: Map[String, String]): BartTransformer.this.type

  146. def setStopTokenIds(value: Array[Int]): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  147. def setTask(value: String): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  148. def setTemperature(value: Double): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  149. def setTopK(value: Int): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  150. def setTopP(value: Double): BartTransformer.this.type

    Definition Classes
    HasGeneratorProperties
  151. def setUseCache(value: Boolean): BartTransformer.this.type
    Attributes
    protected
  152. def setVocabulary(value: Map[String, Int]): BartTransformer.this.type

  153. val signatures: MapFeature[String, String]

    It contains TF model signatures for the laded saved model

  154. val stopTokenIds: IntArrayParam

    Stop tokens to terminate the generation

    Stop tokens to terminate the generation

    Definition Classes
    HasGeneratorProperties
  155. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  156. val task: Param[String]

    Set transformer task, e.g.

    Set transformer task, e.g. "summarize:" (Default: "").

    Definition Classes
    HasGeneratorProperties
  157. val temperature: DoubleParam

    The value used to module the next token probabilities (Default: 1.0)

    The value used to module the next token probabilities (Default: 1.0)

    Definition Classes
    HasGeneratorProperties
  158. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  159. val topK: IntParam

    The number of highest probability vocabulary tokens to keep for top-k-filtering (Default: 50)

    The number of highest probability vocabulary tokens to keep for top-k-filtering (Default: 50)

    Definition Classes
    HasGeneratorProperties
  160. val topP: DoubleParam

    If set to float < 1.0, only the most probable tokens with probabilities that add up to topP or higher are kept for generation (Default: 1.0)

    If set to float < 1.0, only the most probable tokens with probabilities that add up to topP or higher are kept for generation (Default: 1.0)

    Definition Classes
    HasGeneratorProperties
  161. 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
  162. def transform(dataset: Dataset[_], paramMap: ParamMap): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" )
  163. def transform(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): DataFrame
    Definition Classes
    Transformer
    Annotations
    @Since( "2.0.0" ) @varargs()
  164. 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
  165. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  166. val uid: String
    Definition Classes
    BartTransformer → Identifiable
  167. val useCache: BooleanParam

    Cache internal state of the model to improve performance

  168. 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
  169. val vocabulary: MapFeature[String, Int]

    Vocabulary used to encode the words to ids with bpeTokenizer.encode

  170. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  171. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  172. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  173. def wrapColumnMetadata(col: Column): Column
    Attributes
    protected
    Definition Classes
    RawAnnotator
  174. def write: MLWriter
    Definition Classes
    ParamsAndFeaturesWritable → DefaultParamsWritable → MLWritable
  175. def writeOnnxModel(path: String, spark: SparkSession, onnxWrapper: OnnxWrapper, suffix: String, fileName: String): Unit
    Definition Classes
    WriteOnnxModel
  176. def writeOnnxModels(path: String, spark: SparkSession, onnxWrappersWithNames: Seq[(OnnxWrapper, String)], suffix: String): Unit
    Definition Classes
    WriteOnnxModel
  177. def writeTensorflowHub(path: String, tfPath: String, spark: SparkSession, suffix: String = "_use"): Unit
    Definition Classes
    WriteTensorflowModel
  178. def writeTensorflowModel(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None): Unit
    Definition Classes
    WriteTensorflowModel
  179. def writeTensorflowModelV2(path: String, spark: SparkSession, tensorflow: TensorflowWrapper, suffix: String, filename: String, configProtoBytes: Option[Array[Byte]] = None, savedSignatures: Option[Map[String, String]] = None): Unit
    Definition Classes
    WriteTensorflowModel

Inherited from HasGeneratorProperties

Inherited from HasEngine

Inherited from WriteOnnxModel

Inherited from WriteTensorflowModel

Inherited from HasBatchedAnnotate[BartTransformer]

Inherited from AnnotatorModel[BartTransformer]

Inherited from CanBeLazy

Inherited from RawAnnotator[BartTransformer]

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from HasOutputAnnotatorType

Inherited from ParamsAndFeaturesWritable

Inherited from HasFeatures

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from Model[BartTransformer]

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.

Members

Parameter setters

Parameter getters