WordSegmenterApproach

Trains a WordSegmenter which tokenizes non-english or non-whitespace separated texts.

Many languages are not whitespace separated and their sentences are a concatenation of many symbols, like Korean, Japanese or Chinese. Without understanding the language, splitting the words into their corresponding tokens is impossible. The WordSegmenter is trained to understand these languages and split them into semantically correct parts.

For instantiated/pretrained models, see WordSegmenterModel.

To train your own model, a training dataset consisting of Part-Of-Speech tags is required. The data has to be loaded into a dataframe, where the column is an Annotation of type "POS". This can be set with setPosColumn.

Tip: The helper class POS might be useful to read training data into data frames.

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

Example

In this example, "chinese_train.utf8" is in the form of

十|LL 四|RR 不|LL 是|RR 四|LL 十|RR

and is loaded with the POS class to create a dataframe of "POS" type Annotations.

import com.johnsnowlabs.nlp.base.DocumentAssembler
import com.johnsnowlabs.nlp.annotators.ws.WordSegmenterApproach
import com.johnsnowlabs.nlp.training.POS
import org.apache.spark.ml.Pipeline

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

val wordSegmenter = new WordSegmenterApproach()
  .setInputCols("document")
  .setOutputCol("token")
  .setPosColumn("tags")
  .setNIterations(5)

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

val trainingDataSet = POS().readDataset(
  spark,
  "src/test/resources/word-segmenter/chinese_train.utf8"
)

val pipelineModel = pipeline.fit(trainingDataSet)

Linear Supertypes

PerceptronTrainingUtils, PerceptronUtils, AnnotatorApproach[WordSegmenterModel], CanBeLazy, DefaultParamsWritable, MLWritable, HasOutputAnnotatorType, HasOutputAnnotationCol, HasInputAnnotationCols, Estimator[WordSegmenterModel], PipelineStage, Logging, Params, Serializable, Serializable, Identifiable, AnyRef, Any

Instance Constructors

new WordSegmenterApproach()

Annotator reference id.
Annotator reference id. Used to identify elements in metadata or to refer to this annotator type
new WordSegmenterApproach(uid: String)

uid
required uid for storing annotator to disk

Type Members

type AnnotatorType = String

Definition Classes
HasOutputAnnotatorType

Value Members

final def !=(arg0: Any): Boolean

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

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

Attributes
protected
Definition Classes
Params
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): WordSegmenterModel

Attributes
protected
Definition Classes
AnnotatorApproach
val ambiguityThreshold: DoubleParam

How much percentage of total amount of words are covered to be marked as frequent (Default: 0.97)
final def asInstanceOf[T0]: T0

Definition Classes
Any
def beforeTraining(spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
def buildTagBook(taggedSentences: Array[TaggedSentence], frequencyThreshold: Int, ambiguityThreshold: Double): Map[String, String]

Finds very frequent tags on a word in training, and marks them as non ambiguous based on tune parameters ToDo: Move such parameters to configuration
Finds very frequent tags on a word in training, and marks them as non ambiguous based on tune parameters ToDo: Move such parameters to configuration
taggedSentences
Takes entire tagged sentences to find frequent tags
frequencyThreshold
How many times at least a tag on a word to be marked as frequent
ambiguityThreshold
How much percentage of total amount of words are covered to be marked as frequent

Definition Classes
PerceptronTrainingUtils
final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

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

Definition Classes
Params
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def copy(extra: ParamMap): Estimator[WordSegmenterModel]

Definition Classes
AnnotatorApproach → Estimator → PipelineStage → Params
def copyValues[T <: Params](to: T, extra: ParamMap): T

Attributes
protected
Definition Classes
Params
final def defaultCopy[T <: Params](extra: ParamMap): T

Attributes
protected
Definition Classes
Params
val description: String

Definition Classes
WordSegmenterApproach → AnnotatorApproach
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

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

Definition Classes
Params
def explainParams(): String

Definition Classes
Params
final def extractParamMap(): ParamMap

Definition Classes
Params
final def extractParamMap(extra: ParamMap): ParamMap

Definition Classes
Params
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def fit(dataset: Dataset[_]): WordSegmenterModel

Definition Classes
AnnotatorApproach → Estimator
def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[WordSegmenterModel]

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], paramMap: ParamMap): WordSegmenterModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" )
def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): WordSegmenterModel

Definition Classes
Estimator
Annotations
@Since( "2.0.0" ) @varargs()
val frequencyThreshold: IntParam

How many times at least a tag on a word to be marked as frequent (Default: 20)
def generatesTagBook(dataset: Dataset[_]): Array[TaggedSentence]

Generates TagBook, which holds all the word to tags mapping that are not ambiguous
Generates TagBook, which holds all the word to tags mapping that are not ambiguous

Definition Classes
PerceptronTrainingUtils
final def get[T](param: Param[T]): Option[T]

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

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

Definition Classes
Params
def getInputCols: Array[String]

returns
input annotations columns currently used

Definition Classes
HasInputAnnotationCols
def getLazyAnnotator: Boolean

Definition Classes
CanBeLazy
def getNIterations: Int
final def getOrDefault[T](param: Param[T]): T

Definition Classes
Params
final def getOutputCol: String

Gets annotation column name going to generate
Gets annotation column name going to generate

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

Definition Classes
Params
final def hasDefault[T](param: Param[T]): Boolean

Definition Classes
Params
def hasParam(paramName: String): Boolean

Definition Classes
Params
def hashCode(): Int

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

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

Attributes
protected
Definition Classes
Logging
val inputAnnotatorTypes: Array[String]

Input Annotator Types: DOCUMENT
Input Annotator Types: DOCUMENT

Definition Classes
WordSegmenterApproach → HasInputAnnotationCols
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
final def isDefined(param: Param[_]): Boolean

Definition Classes
Params
final def isInstanceOf[T0]: Boolean

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

Definition Classes
Params
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
val lazyAnnotator: BooleanParam

Definition Classes
CanBeLazy
def log: Logger

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

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

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

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

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

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

Attributes
protected
Definition Classes
Logging
def logName: String

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

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

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

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

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

Attributes
protected
Definition Classes
HasInputAnnotationCols
val nIterations: IntParam

Number of iterations in training, converges to better accuracy (Default: 5)
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def onTrained(model: WordSegmenterModel, spark: SparkSession): Unit

Definition Classes
AnnotatorApproach
val optionalInputAnnotatorTypes: Array[String]

Definition Classes
HasInputAnnotationCols
val outputAnnotatorType: AnnotatorType

Output Annotator Types: TOKEN
Output Annotator Types: TOKEN

Definition Classes
WordSegmenterApproach → HasOutputAnnotatorType
final val outputCol: Param[String]

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

Definition Classes
Params
val posCol: Param[String]

Column of Array of POS tags that match tokens
def save(path: String): Unit

Definition Classes
MLWritable
Annotations
@Since( "1.6.0" ) @throws( ... )
final def set(paramPair: ParamPair[_]): WordSegmenterApproach.this.type

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

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

Definition Classes
Params
def setAmbiguityThreshold(value: Double): WordSegmenterApproach.this.type
final def setDefault(paramPairs: ParamPair[_]*): WordSegmenterApproach.this.type

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

Attributes
protected
Definition Classes
Params
def setFrequencyThreshold(value: Int): WordSegmenterApproach.this.type
final def setInputCols(value: String*): WordSegmenterApproach.this.type

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

Overrides required annotators column if different than default
Overrides required annotators column if different than default

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

Definition Classes
CanBeLazy
def setNIterations(value: Int): WordSegmenterApproach.this.type
final def setOutputCol(value: String): WordSegmenterApproach.this.type

Overrides annotation column name when transforming
Overrides annotation column name when transforming

Definition Classes
HasOutputAnnotationCol
def setPosColumn(value: String): WordSegmenterApproach.this.type
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
Identifiable → AnyRef → Any
def train(dataset: Dataset[_], recursivePipeline: Option[PipelineModel]): WordSegmenterModel

Definition Classes
WordSegmenterApproach → AnnotatorApproach
def trainPerceptron(nIterations: Int, initialModel: TrainingPerceptronLegacy, taggedSentences: Array[TaggedSentence], taggedWordBook: Map[String, String]): AveragedPerceptron

Iterates for training
Iterates for training

Definition Classes
PerceptronTrainingUtils
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
def transformSchema(schema: StructType, logging: Boolean): StructType

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

required uid for storing annotator to disk
required uid for storing annotator to disk

Definition Classes
WordSegmenterApproach → Identifiable
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
final def wait(): Unit

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

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

Definition Classes
AnyRef
Annotations
@throws( ... )
def write: MLWriter

Definition Classes
DefaultParamsWritable → MLWritable

Inherited from PerceptronTrainingUtils

Inherited from PerceptronUtils

Inherited from AnnotatorApproach[WordSegmenterModel]

Inherited from CanBeLazy

Inherited from DefaultParamsWritable

Inherited from MLWritable

Inherited from HasOutputAnnotatorType

Inherited from HasOutputAnnotationCol

Inherited from HasInputAnnotationCols

Inherited from Estimator[WordSegmenterModel]

Inherited from PipelineStage

Inherited from Logging

Inherited from Params

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.

Related Docs: object WordSegmenterApproach | package ws

class WordSegmenterApproach extends AnnotatorApproach[WordSegmenterModel] with PerceptronTrainingUtils

Example

Instance Constructors

new WordSegmenterApproach()

new WordSegmenterApproach(uid: String)

Type Members

type AnnotatorType = String

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def $[T](param: Param[T]): T

final def ==(arg0: Any): Boolean

def _fit(dataset: Dataset[_], recursiveStages: Option[PipelineModel]): WordSegmenterModel

val ambiguityThreshold: DoubleParam

final def asInstanceOf[T0]: T0

def beforeTraining(spark: SparkSession): Unit

def buildTagBook(taggedSentences: Array[TaggedSentence], frequencyThreshold: Int, ambiguityThreshold: Double): Map[String, String]

final def checkSchema(schema: StructType, inputAnnotatorType: String): Boolean

final def clear(param: Param[_]): WordSegmenterApproach.this.type

def clone(): AnyRef

final def copy(extra: ParamMap): Estimator[WordSegmenterModel]

def copyValues[T <: Params](to: T, extra: ParamMap): T

final def defaultCopy[T <: Params](extra: ParamMap): T

val description: String

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def explainParam(param: Param[_]): String

def explainParams(): String

final def extractParamMap(): ParamMap

final def extractParamMap(extra: ParamMap): ParamMap

def finalize(): Unit

final def fit(dataset: Dataset[_]): WordSegmenterModel

def fit(dataset: Dataset[_], paramMaps: Array[ParamMap]): Seq[WordSegmenterModel]

def fit(dataset: Dataset[_], paramMap: ParamMap): WordSegmenterModel

def fit(dataset: Dataset[_], firstParamPair: ParamPair[_], otherParamPairs: ParamPair[_]*): WordSegmenterModel

val frequencyThreshold: IntParam

def generatesTagBook(dataset: Dataset[_]): Array[TaggedSentence]

final def get[T](param: Param[T]): Option[T]

final def getClass(): Class[_]

final def getDefault[T](param: Param[T]): Option[T]

def getInputCols: Array[String]

def getLazyAnnotator: Boolean

def getNIterations: Int

final def getOrDefault[T](param: Param[T]): T

final def getOutputCol: String

def getParam(paramName: String): Param[Any]

final def hasDefault[T](param: Param[T]): Boolean

def hasParam(paramName: String): Boolean

def hashCode(): Int

def initializeLogIfNecessary(isInterpreter: Boolean, silent: Boolean): Boolean

def initializeLogIfNecessary(isInterpreter: Boolean): Unit

val inputAnnotatorTypes: Array[String]

final val inputCols: StringArrayParam

final def isDefined(param: Param[_]): Boolean

final def isInstanceOf[T0]: Boolean

final def isSet(param: Param[_]): Boolean

def isTraceEnabled(): Boolean

val lazyAnnotator: BooleanParam

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

def msgHelper(schema: StructType): String

val nIterations: IntParam

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def onTrained(model: WordSegmenterModel, spark: SparkSession): Unit

val optionalInputAnnotatorTypes: Array[String]

val outputAnnotatorType: AnnotatorType