Class/Object

org.clulab.dynet

Metal

Related Docs: object Metal | package dynet

Permalink

class Metal extends AnyRef

Multi-task learning (MeTaL) for sequence modeling Designed to model any sequence task (e.g., POS tagging, NER), and SRL

Linear Supertypes
AnyRef, Any
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. Metal
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Instance Constructors

  1. new Metal(taskManagerOpt: Option[TaskManager], parameters: ParameterCollection, modelOpt: Option[IndexedSeq[Layers]])

    Permalink

Value Members

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

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

    Permalink
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean

    Permalink
    Definition Classes
    AnyRef → Any
  4. final def asInstanceOf[T0]: T0

    Permalink
    Definition Classes
    Any
  5. def batchBackprop(batchLosses: ExpressionVector, trainer: SafeTrainer): Float

    Permalink
  6. def chooseOptimalPreds(predsWithScores: IndexedSeq[IndexedSeq[(String, Float)]], goldLabels: IndexedSeq[String], topK: Int): IndexedSeq[String]

    Permalink

    Ceiling method that chooses the gold dependency for each modifier from the top K predictions

  7. def clone(): AnyRef

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  8. final def eq(arg0: AnyRef): Boolean

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

    Permalink
    Definition Classes
    AnyRef → Any
  10. def evaluate(taskId: Int, taskName: String, sentences: Array[Array[Row]], name: String, epoch: Int): (Double, Double, Double, Double)

    Permalink

    Computes accuracy/P/R/F1 for the evaluation dataset of the given task Where possible, it also saves CoNLL-2003 compatible files of the output

  11. def evaluate(taskId: Int, taskName: String, sentences: Array[Array[Row]]): (Double, Double, Double, Double)

    Permalink
  12. def evaluate(taskId: Int, taskName: String, sentences: Array[Array[Row]], epoch: Int): (Double, Double, Double, Double)

    Permalink
  13. def finalize(): Unit

    Permalink
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  14. final def getClass(): Class[_]

    Permalink
    Definition Classes
    AnyRef → Any
  15. def hashCode(): Int

    Permalink
    Definition Classes
    AnyRef → Any
  16. def initialize(): Array[Layers]

    Permalink
    Attributes
    protected
  17. final def isInstanceOf[T0]: Boolean

    Permalink
    Definition Classes
    Any
  18. def mkVocabularies(): (Array[Counter[String]], Array[Counter[String]])

    Permalink
    Attributes
    protected
  19. lazy val model: IndexedSeq[Layers]

    Permalink
    Attributes
    protected
  20. final def ne(arg0: AnyRef): Boolean

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

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

    Permalink
    Definition Classes
    AnyRef
  23. val parameters: ParameterCollection

    Permalink
  24. def parse(sentence: AnnotatedSentence, constEmbeddings: ConstEmbeddingParameters): IndexedSeq[(Int, String)]

    Permalink

    Custom method for the parsing algorithm

    Custom method for the parsing algorithm

    sentence

    Input sentence

    constEmbeddings

    Constant embeddings for this sentence

    returns

    Tuple of (head, label) for each word in the sentence

  25. def parseWithEisner(sentence: AnnotatedSentence, constEmbeddings: ConstEmbeddingParameters, topK: Int, lambda: Float): IndexedSeq[(Int, String)]

    Permalink
  26. def predict(taskId: Int, sentence: AnnotatedSentence, modHeadPairsOpt: Option[IndexedSeq[ModifierHeadPair]], constEmbeddings: ConstEmbeddingParameters): IndexedSeq[String]

    Permalink
  27. def predictJointly(sentence: AnnotatedSentence, constEmbeddings: ConstEmbeddingParameters): IndexedSeq[IndexedSeq[String]]

    Permalink
  28. def predictWithScores(taskId: Int, sentence: AnnotatedSentence, modHeadPairsOpt: Option[IndexedSeq[ModifierHeadPair]], constEmbeddings: ConstEmbeddingParameters, applySoftmax: Boolean = true): IndexedSeq[IndexedSeq[(String, Float)]]

    Permalink
  29. def save(baseFilename: String): Unit

    Permalink
  30. final def synchronized[T0](arg0: ⇒ T0): T0

    Permalink
    Definition Classes
    AnyRef
  31. def taskManager: TaskManager

    Permalink
  32. val taskManagerOpt: Option[TaskManager]

    Permalink
  33. def test(): Unit

    Permalink
  34. def toString(): String

    Permalink
    Definition Classes
    AnyRef → Any
  35. def train(modelNamePrefix: String): Unit

    Permalink
  36. final def wait(): Unit

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

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

    Permalink
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from AnyRef

Inherited from Any

Ungrouped