OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 aperta il 22 mag 2018

Vedi su GitHub
 (5 commenti) (0 reazioni) (0 assegnatari)Python (394 fork)batch import
enhancementhelp wanted

Metriche repository

Star
 (1428 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

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)

Guida contributor