OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 opened on 2018年5月22日

GitHub で見る
 (5 comments) (0 reactions) (0 assignees)Python (394 forks)batch import
enhancementhelp wanted

Repository metrics

Stars
 (1,428 stars)
PR merge metrics
 (30d に merged PR はありません)

説明

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)

コントリビューターガイド