OpenNMT/OpenNMT-tf

CNN decoder

Open

#884 opened on Sep 30, 2021

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (1,428 stars) (394 forks)batch import
enhancementhelp wanted

Description

Hello,

Is there a plan to implement fully CNN seq2seq models? like this paper from Facebook https://arxiv.org/pdf/1705.03122.pdf I can see that there is a CNN encoder, but still not a decoder. It would be great to have it as well in OpenNMT-tf.

Thanks

Contributor guide

Tech stack
pythontensorflow
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
seq2seq modelsCNNsTensorFlowOpenNMT tf
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
15
Research direction
Investigate the referenced paper (arXiv:1705.03122) for CNN seq2seq architecture. Examine the existing CNN encoder implementation in OpenNMT tf to understand the codebase. Propose a design for a CNN decoder and discuss with maintainers for guidance.