OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 ouverte le 22 mai 2018

Voir sur GitHub
 (5 commentaires) (0 réactions) (0 assignés)Python (394 forks)batch import
enhancementhelp wanted

Métriques du dépôt

Stars
 (1 428 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

Similarly to the ParallelEncoder, a ParallelDecoder setup could allow multi-task learning. This should not be too hard to implement but we need to take care of some details:

  • support separate values for the decoding parameters (beam_width, length_penalty, etc.),
  • parts of SequenceToSequence assume a single output head (e.g. loss computation, reverse vocabulary lookup, exported outputs for model serving, etc. which should be moved in the decoder itself)

Guide contributeur