dynet

Type Members

1. case class AnnotatedSentence(words: IndexedSeq[String], posTags: Option[IndexedSeq[String]] = None, neTags: Option[IndexedSeq[String]] = None) extends Product with Serializable

   

2. class Chart extends AnyRef

   

3. class CoNLLSRLToMetal extends AnyRef

   

   Reads a CoNLL-2008 formatted file (containing semantic roles) and converts it to our own Metal format User: mihais Date: 5/5/15 Last Modified: 08/05/2020: Added the latest Metal format Update for Scala 2.12: bug #10151 workaround.

4. case class ConstEmbeddingParameters(collection: ParameterCollection, lookupParameters: LookupParameter, w2i: Map[String, Int]) extends Product with Serializable

   

   Stores lookup parameters + the map from strings to ids

5. class ConstEmbeddingsGlove extends AnyRef

   

6. case class Dependency(mod: Int, head: Int, score: Float, rank: Int, label: String = "") extends Product with Serializable

   

   Stores one dependency for the Eisner algorithm Indexes for head and mod start at 1 for the first word in the sentence; 0 is reserved for root

7. case class DualLabel(modifier: Int, head: Int, label: String) extends Label with Product with Serializable

   

   Label information for a dual task that classifies pairs of words (modifier and head) Note: offsets for modifier and head start at 0.

   Label information for a dual task that classifies pairs of words (modifier and head) Note: offsets for modifier and head start at 0. "root" heads have index -1

8. class Eisner extends AnyRef

   

9. class EmbeddingLayer extends InitialLayer

   

   This layer takes a sequence of words and produces a sequence of Expression that stores the words' full embeddings

10. trait FinalLayer extends Saveable

    

11. abstract class ForwardLayer extends FinalLayer

    

12. class GreedyForwardLayer extends ForwardLayer

    

13. trait InitialLayer extends Saveable

    

    First layer that occurs in a sequence modeling architecture: goes from words to Expressions

14. trait IntermediateLayer extends Saveable

    

    Intermediate layer in a sequence modeling architecture: goes from ExpressionVector to ExpressionVector

15. trait Label extends AnyRef

    

16. class Layers extends Saveable

    

    A sequence of layers that implements a complete NN architecture for sequence modeling

17. class Metal extends AnyRef

    

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

18. class MetalRowReader extends RowReader

    

19. class MetalShell extends Shell

    

20. case class ModifierHeadPair(modifier: Int, head: Int) extends Product with Serializable

    

    Indexes for pairs of words (modifier and head) Note: offsets for modifier and head start at 0.

    Indexes for pairs of words (modifier and head) Note: offsets for modifier and head start at 0. "root" heads have index -1

21. case class PrimalLabel(label: String) extends Label with Product with Serializable

    

22. class RnnLayer extends IntermediateLayer

    

    This layer applies a biLSTM over the sequence of Expressions produced by a previous layer

23. trait RowReader extends AnyRef

    

24. class SafeTrainer extends AnyRef

    

25. trait Saveable extends AnyRef

    

26. case class ScoreCounts(correct: Int = 0, gold: Int = 0, predicted: Int = 0) extends Product with Serializable

    

27. class ScoreCountsByLabel extends AnyRef

    

28. class SentenceIterator extends Iterator[(Int, Array[Row])]

    

29. case class Shard(taskId: Int, startPosition: Int, endPosition: Int) extends Product with Serializable

    

30. class Span extends AnyRef

    

31. class Task extends AnyRef

    

32. class TaskManager extends Configured

    

    Manages the tasks in LstmCrfMtl

33. class Utils extends AnyRef

    

34. class ViterbiForwardLayer extends ForwardLayer