case classOutputEmbeddingTransform[FV](numOutputs: Int, outputDim: Int, innerTransform: Transform[FV, DenseVector[Double]], coarsenerForInitialization: Option[(Int) ⇒ Int] = None) extends OutputTransform[FV, DenseVector[Double]] with Product with Serializable
Output embedding technique described in section 6 of
http://www.eecs.berkeley.edu/~gdurrett/papers/durrett-klein-acl2015.pdf
Basically learns a dictionary for the output as well as an affine transformation
in order to produce the vector that gets combined with the input in the final
bilinear product.
Linear Supertypes
Product, Equals, OutputTransform[FV, DenseVector[Double]], Serializable, Serializable, AnyRef, Any
case classOutputLayer(embeddings: DenseMatrix[Double], bias: DenseVector[Double], innerLayer: Layer) extends OutputTransform.OutputLayer[FV, DenseVector[Double]] with Product with Serializable
Value Members
final def!=(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final def##(): Int
Definition Classes
AnyRef → Any
final def==(arg0: Any): Boolean
Definition Classes
AnyRef → Any
final defasInstanceOf[T0]: T0
Definition Classes
Any
defclipEmbeddingNorms(weights: DenseVector[Double]): Unit
defclipHiddenWeightVectors(weights: DenseVector[Double], norm: Double, outputLayer: Boolean): Unit
Output embedding technique described in section 6 of http://www.eecs.berkeley.edu/~gdurrett/papers/durrett-klein-acl2015.pdf Basically learns a dictionary for the output as well as an affine transformation in order to produce the vector that gets combined with the input in the final bilinear product.