class SentenceDetectorDLApproach extends AnnotatorApproach[SentenceDetectorDLModel]

Trains an annotator that detects sentence boundaries using a deep learning approach.

For pretrained models see SentenceDetectorDLModel.

Currently, only the CNN model is supported for training, but in the future the architecture of the model can be set with setModelArchitecture.

The default model "cnn" is based on the paper Deep-EOS: General-Purpose Neural Networks for Sentence Boundary Detection (2020, Stefan Schweter, Sajawel Ahmed) using a CNN architecture. We also modified the original implementation a little bit to cover broken sentences and some impossible end of line chars.

Each extracted sentence can be returned in an Array or exploded to separate rows, if explodeSentences is set to true.

For extended examples of usage, see the Spark NLP Workshop and the SentenceDetectorDLSpec.

Example

The training process needs data, where each data point is a sentence.

In this example the train.txt file has the form of

...
Slightly more moderate language would make our present situation – namely the lack of progress – a little easier.
His political successors now have great responsibilities to history and to the heritage of values bequeathed to them by Nelson Mandela.
...

where each line is one sentence. Training can then be started like so:

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.sentence_detector_dl.SentenceDetectorDLApproach
import org.apache.spark.ml.Pipeline

val trainingData = spark.read.text("train.txt").toDF("text")

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

val sentenceDetector = new SentenceDetectorDLApproach()
  .setInputCols(Array("document"))
  .setOutputCol("sentences")
  .setEpochsNumber(100)

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

val model = pipeline.fit(trainingData)
See also

SentenceDetectorDLModel for pretrained models

SentenceDetector for non deep learning extraction

Linear Supertypes
AnnotatorApproach[SentenceDetectorDLModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[SentenceDetectorDLModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any
Ordering
  1. Grouped
  2. Alphabetic
  3. By Inheritance
Inherited
  1. SentenceDetectorDLApproach
  2. AnnotatorApproach
  3. CanBeLazy
  4. DefaultParamsWritable
  5. MLWritable
  6. HasOutputAnnotatorType
  7. HasOutputAnnotationCol
  8. HasInputAnnotationCols
  9. Estimator
  10. PipelineStage
  11. Logging
  12. Params
  13. Serializable
  14. Serializable
  15. Identifiable
  16. AnyRef
  17. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

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

    uid

    required uid for storing annotator to disk

Type Members

  1. 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. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  5. def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): SentenceDetectorDLModel
    Attributes
    protected
    Definition Classes
    AnnotatorApproach
  6. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  7. def beforeTraining(spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  8. final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  9. final def clear(param: Param[_]): SentenceDetectorDLApproach.this.type
    Definition Classes
    Params
  10. def clone(): AnyRef
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  11. final def copy(extra: ParamMap): Estimator[SentenceDetectorDLModel]
    Definition Classes
    AnnotatorApproach → Estimator → PipelineStage → Params
  12. def copyValues[T <: Params](to: T, extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  13. val customBounds: StringArrayParam

    Characters used to explicitly mark sentence bounds (Default: None)

  14. final def defaultCopy[T <: Params](extra: ParamMap): T
    Attributes
    protected
    Definition Classes
    Params
  15. val description: String

    Trains TensorFlow model for multi-class text classification

    Trains TensorFlow model for multi-class text classification

    Definition Classes
    SentenceDetectorDLApproachAnnotatorApproach
  16. val epochsNumber: IntParam

    Maximum number of epochs to train (Default: 5)

  17. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  18. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  19. def explainParam(param: Param[_]): String
    Definition Classes
    Params
  20. def explainParams(): String
    Definition Classes
    Params
  21. def explodeSentences: BooleanParam

    A flag indicating whether to split sentences into different Dataset rows.

    A flag indicating whether to split sentences into different Dataset rows. Useful for higher parallelism in fat rows (Default: false)

  22. final def extractParamMap(): ParamMap
    Definition Classes
    Params
  23. final def extractParamMap(extra: ParamMap): ParamMap
    Definition Classes
    Params
  24. def finalize(): Unit
    Attributes
    protected[lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  25. final def fit(dataset: Dataset[_]): SentenceDetectorDLModel
    Definition Classes
    AnnotatorApproach → Estimator
  26. def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[SentenceDetectorDLModel]
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  27. def fit(dataset: Dataset[_], paramMap: ParamMap): SentenceDetectorDLModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" )
  28. def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): SentenceDetectorDLModel
    Definition Classes
    Estimator
    Annotations
    @Since( "2.0.0" ) @varargs()
  29. final def get[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  30. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  31. def getCustomBounds: Array[String]

    Custom sentence separator text

  32. final def getDefault[T](param: Param[T]): Option[T]
    Definition Classes
    Params
  33. def getEpochsNumber: Int

    Maximum number of epochs to train (Default: 5)

  34. def getExplodeSentences: Boolean

    Whether to split sentences into different Dataset rows.

    Whether to split sentences into different Dataset rows. Useful for higher parallelism in fat rows. Defaults to false.

  35. def getGraphFilename: String
  36. def getImpossiblePenultimates: Array[String]

    Get impossible penultimates

  37. def getInputCols: Array[String]

    returns

    input annotations columns currently used

    Definition Classes
    HasInputAnnotationCols
  38. def getLazyAnnotator: Boolean
    Definition Classes
    CanBeLazy
  39. def getMaxLength: Int

    Get the maximum allowed length for each sentence

  40. def getMinLength: Int

    Get the minimum allowed length for each sentence

  41. def getModel: String

    Get model architecture

  42. final def getOrDefault[T](param: Param[T]): T
    Definition Classes
    Params
  43. final def getOutputCol: String

    Gets annotation column name going to generate

    Gets annotation column name going to generate

    Definition Classes
    HasOutputAnnotationCol
  44. def getOutputLogsPath: String

    Get output logs path

  45. def getParam(paramName: String): Param[Any]
    Definition Classes
    Params
  46. def getSplitLength: Int

    Length at which sentences will be forcibly split

  47. def getUseCustomBoundsOnly: Boolean

    Use only custom bounds without considering those of Pragmatic Segmenter.

    Use only custom bounds without considering those of Pragmatic Segmenter. Defaults to false. Needs customBounds.

  48. def getValidationSplit: Float

    Choose the proportion of training dataset to be validated against the model on each Epoch.

    Choose the proportion of training dataset to be validated against the model on each Epoch. The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

  49. final def hasDefault[T](param: Param[T]): Boolean
    Definition Classes
    Params
  50. def hasParam(paramName: String): Boolean
    Definition Classes
    Params
  51. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  52. val impossiblePenultimates: StringArrayParam

    Impossible penultimates, which should not be split on Default:

    Impossible penultimates, which should not be split on Default:

    Array(
      "Bros", "No", "al", "vs", "etc", "Fig", "Dr", "Prof", "PhD", "MD", "Co", "Corp", "Inc",
      "bros", "VS", "Vs", "ETC", "fig", "dr", "prof", "PHD", "phd", "md", "co", "corp", "inc",
      "Jan", "Feb", "Mar", "Apr", "Jul", "Aug", "Sep", "Sept", "Oct", "Nov", "Dec",
      "St", "st",
      "AM", "PM", "am", "pm",
      "e.g", "f.e", "i.e"
    )
  53. def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  54. def initializeLogIfNecessary(isInterpreter: Boolean): Unit
    Attributes
    protected
    Definition Classes
    Logging
  55. val inputAnnotatorTypes: Array[AnnotatorType]

    Input annotator type : DOCUMENT

    Input annotator type : DOCUMENT

    Definition Classes
    SentenceDetectorDLApproachHasInputAnnotationCols
  56. 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
  57. final def isDefined(param: Param[_]): Boolean
    Definition Classes
    Params
  58. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  59. final def isSet(param: Param[_]): Boolean
    Definition Classes
    Params
  60. def isTraceEnabled(): Boolean
    Attributes
    protected
    Definition Classes
    Logging
  61. val lazyAnnotator: BooleanParam
    Definition Classes
    CanBeLazy
  62. def log: Logger
    Attributes
    protected
    Definition Classes
    Logging
  63. def logDebug(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  64. def logDebug(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  65. def logError(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  66. def logError(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  67. def logInfo(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  68. def logInfo(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  69. def logName: String
    Attributes
    protected
    Definition Classes
    Logging
  70. def logTrace(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  71. def logTrace(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  72. def logWarning(msg: ⇒ String, throwable: Throwable): Unit
    Attributes
    protected
    Definition Classes
    Logging
  73. def logWarning(msg: ⇒ String): Unit
    Attributes
    protected
    Definition Classes
    Logging
  74. val maxLength: IntParam

    Set the maximum allowed length for each sentence (Ignored if not set)

  75. val minLength: IntParam

    Set the minimum allowed length for each sentence (Default: 0)

  76. var modelArchitecture: Param[String]

    Model architecture (Default: "cnn")

  77. def msgHelper(schema: StructType): String
    Attributes
    protected
    Definition Classes
    HasInputAnnotationCols
  78. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  79. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  80. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  81. def onTrained(model: SentenceDetectorDLModel, spark: SparkSession): Unit
    Definition Classes
    AnnotatorApproach
  82. val optionalInputAnnotatorTypes: Array[String]
    Definition Classes
    HasInputAnnotationCols
  83. val outputAnnotatorType: String

    Output annotator type : DOCUMENT

    Output annotator type : DOCUMENT

    Definition Classes
    SentenceDetectorDLApproachHasOutputAnnotatorType
  84. final val outputCol: Param[String]
    Attributes
    protected
    Definition Classes
    HasOutputAnnotationCol
  85. val outputLogsPath: Param[String]

    Path to folder to output logs (Default: "") If no path is specified, no logs are generated

  86. lazy val params: Array[Param[_]]
    Definition Classes
    Params
  87. def save(path: String): Unit
    Definition Classes
    MLWritable
    Annotations
    @Since( "1.6.0" ) @throws( ... )
  88. final def set(paramPair: ParamPair[_]): SentenceDetectorDLApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  89. final def set(param: String, value: Any): SentenceDetectorDLApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  90. final def set[T](param: Param[T], value: T): SentenceDetectorDLApproach.this.type
    Definition Classes
    Params
  91. def setCustomBounds(value: Array[String]): SentenceDetectorDLApproach.this.type

    Custom sentence separator text

  92. final def setDefault(paramPairs: ParamPair[_]*): SentenceDetectorDLApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  93. final def setDefault[T](param: Param[T], value: T): SentenceDetectorDLApproach.this.type
    Attributes
    protected
    Definition Classes
    Params
  94. def setEpochsNumber(epochs: Int): SentenceDetectorDLApproach.this.type

    Maximum number of epochs to train (Default: 5)

  95. def setExplodeSentences(value: Boolean): SentenceDetectorDLApproach.this.type

    Whether to split sentences into different Dataset rows.

    Whether to split sentences into different Dataset rows. Useful for higher parallelism in fat rows. Defaults to false.

  96. def setGraphFile(graphFilename: String): SentenceDetectorDLApproach.this.type
  97. def setImpossiblePenultimates(impossiblePenultimates: Array[String]): SentenceDetectorDLApproach.this.type

    Set impossible penultimates

  98. final def setInputCols(value: String*): SentenceDetectorDLApproach.this.type
    Definition Classes
    HasInputAnnotationCols
  99. def setInputCols(value: Array[String]): SentenceDetectorDLApproach.this.type

    Overrides required annotators column if different than default

    Overrides required annotators column if different than default

    Definition Classes
    HasInputAnnotationCols
  100. def setLazyAnnotator(value: Boolean): SentenceDetectorDLApproach.this.type
    Definition Classes
    CanBeLazy
  101. def setMaxLength(value: Int): SentenceDetectorDLApproach.this.type

    Set the maximum allowed length for each sentence

  102. def setMinLength(value: Int): SentenceDetectorDLApproach.this.type

    Set the minimum allowed length for each sentence

  103. def setModel(modelArchitecture: String): SentenceDetectorDLApproach.this.type

    Set architecture

  104. final def setOutputCol(value: String): SentenceDetectorDLApproach.this.type

    Overrides annotation column name when transforming

    Overrides annotation column name when transforming

    Definition Classes
    HasOutputAnnotationCol
  105. def setOutputLogsPath(outputLogsPath: String): SentenceDetectorDLApproach.this.type

    Set the output log path

  106. def setSplitLength(value: Int): SentenceDetectorDLApproach.this.type

    Length at which sentences will be forcibly split

  107. def setUseCustomBoundsOnly(value: Boolean): SentenceDetectorDLApproach.this.type

    Use only custom bounds without considering those of Pragmatic Segmenter.

    Use only custom bounds without considering those of Pragmatic Segmenter. Defaults to false. Needs customBounds.

  108. def setValidationSplit(validationSplit: Float): SentenceDetectorDLApproach.this.type

    Choose the proportion of training dataset to be validated against the model on each Epoch.

    Choose the proportion of training dataset to be validated against the model on each Epoch. The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

  109. val splitLength: IntParam

    Length at which sentences will be forcibly split (Ignored if not set)

  110. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  111. def toString(): String
    Definition Classes
    Identifiable → AnyRef → Any
  112. def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): SentenceDetectorDLModel
  113. final def transformSchema(schema: StructType): StructType

    requirement for pipeline transformation validation.

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

    Definition Classes
    AnnotatorApproach → PipelineStage
  114. def transformSchema(schema: StructType, logging: Boolean): StructType
    Attributes
    protected
    Definition Classes
    PipelineStage
    Annotations
    @DeveloperApi()
  115. val uid: String
    Definition Classes
    SentenceDetectorDLApproach → Identifiable
  116. val useCustomBoundsOnly: BooleanParam

    Whether to only utilize custom bounds for sentence detection (Default: false)

  117. 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
    AnnotatorApproach
  118. val validationSplit: FloatParam

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f).

    Choose the proportion of training dataset to be validated against the model on each Epoch (Default: 0.0f). The value should be between 0.0 and 1.0 and by default it is 0.0 and off.

  119. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  120. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  121. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... ) @native()
  122. def write: MLWriter
    Definition Classes
    DefaultParamsWritable → MLWritable

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[SentenceDetectorDLModel]

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