OpenNMT/OpenNMT-tf

Multi-decoder setup for multi-task learning

Open

#130 opened on May 22, 2018

View on GitHub
 (5 comments) (0 reactions) (0 assignees)Python (394 forks)batch import
enhancementhelp wanted

Repository metrics

Stars
 (1,428 stars)
PR merge metrics
 (No merged PRs in 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)

Contributor guide

Research direction
Study the existing ParallelEncoder implementation to understand the pattern, then create a ParallelDecoder class with separate decoding parameters. Refactor SequenceToSequence to handle multiple decoders for loss computation and vocabulary lookup.
Tech stack
pythontensorflow
Domain
aibackend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonTensorFlowGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70