epic.parser.models

NeuralModel

class NeuralModel[L, L2, W] extends Model[TreeInstance[L, W]] with ParserExtractable[L, W]

The neural model is really just a

Linear Supertypes
ParserExtractable[L, W], Model[TreeInstance[L, W]], Model[TreeInstance[L, W]], AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. NeuralModel
  2. ParserExtractable
  3. Model
  4. Model
  5. AnyRef
  6. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new NeuralModel(baseModel: SpanModel[L, L2, W], labelFeaturizer: RefinedFeaturizer[L, W, Feature], surfaceFeaturizer: IndexedSplitSpanFeaturizer[W], transform: Transform[FeatureVector, DenseVector[Double]], numOutputs: Int, initialFeatureVal: (Feature) ⇒ Option[Double] = ...)

Type Members

  1. type ExpectedCounts = StandardExpectedCounts[Feature]

    Definition Classes
    ModelModel
  2. type Inference = NeuralInference[L, L2, W]

    Definition Classes
    NeuralModelModel
  3. type Marginal = ParseMarginal[L, W]

    Definition Classes
    NeuralModelModel
  4. type Scorer = GrammarAnchoring[L, W]

    Definition Classes
    NeuralModelModel

Value Members

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

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

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

    Definition Classes
    AnyRef
  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  6. def accumulateCounts(anchoring: Scorer, d: TreeInstance[L, W], m: Marginal, accum: ExpectedCounts, scale: Double): Unit

    Definition Classes
    NeuralModelModel
  7. final def accumulateCounts(inf: Inference, d: TreeInstance[L, W], accum: ExpectedCounts, scale: Double): Unit

    Definition Classes
    Model
  8. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  9. def cacheFeatureWeights(weights: DenseVector[Double], suffix: String = ""): Unit

    Caches the weights using the cache broker.

    Caches the weights using the cache broker.

    Definition Classes
    Model
  10. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  11. def constrainer: Factory[L, W]

    Definition Classes
    NeuralModelParserExtractable
  12. def emptyCounts: StandardExpectedCounts[Feature]

    Definition Classes
    ModelModel
  13. final def eq(arg0: AnyRef): Boolean

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

    Definition Classes
    AnyRef → Any
  15. final def expectedCounts(inf: Inference, d: TreeInstance[L, W], scale: Double = 1.0): ExpectedCounts

    Definition Classes
    Model
  16. def expectedCountsToObjective(ecounts: StandardExpectedCounts[Feature]): (Double, DenseVector[Double])

    Definition Classes
    NeuralModelModelModel
  17. def extractParser(weights: DenseVector[Double])(implicit deb: Debinarizer[L]): Parser[L, W]

    Definition Classes
    NeuralModelParserExtractable
  18. val featureIndex: SegmentedIndex[Feature, Index[Feature]]

    Models have features, and this defines the mapping from indices in the weight vector to features.

    Models have features, and this defines the mapping from indices in the weight vector to features.

    returns

    Definition Classes
    NeuralModelModel
  19. def finalize(): Unit

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

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

    Definition Classes
    AnyRef → Any
  22. def inferenceFromWeights(weights: DenseVector[Double]): Inference

    Definition Classes
    NeuralModelModel
  23. def initialValueForFeature(f: Feature): Double

    Definition Classes
    NeuralModelModel
  24. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  25. def lexicon: Lexicon[L, W]

    Definition Classes
    NeuralModelParserExtractable
  26. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  27. final def notify(): Unit

    Definition Classes
    AnyRef
  28. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  29. def numFeatures: Int

    Definition Classes
    Model
  30. def readCachedFeatureWeights(suffix: String = ""): Option[DenseVector[Double]]

    just saves feature weights to disk as a serialized counter.

    just saves feature weights to disk as a serialized counter. The file is prefix.ser.gz

    Definition Classes
    Model
  31. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  32. def toString(): String

    Definition Classes
    AnyRef → Any
  33. def topology: RuleTopology[L]

    Definition Classes
    NeuralModelParserExtractable
  34. final def wait(): Unit

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

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

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  37. def weightsCacheName: String

    Attributes
    protected
    Definition Classes
    Model

Inherited from ParserExtractable[L, W]

Inherited from Model[TreeInstance[L, W]]

Inherited from Model[TreeInstance[L, W]]

Inherited from AnyRef

Inherited from Any

Ungrouped