OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 aberto em 22 de mai. de 2018

Ver no GitHub
 (5 comments) (0 reactions) (0 assignees)Python (394 forks)batch import
enhancementhelp wanted

Métricas do repositório

Stars
 (1.428 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

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)

Guia do colaborador