facebookresearch/fairseq

key_padding_mask is not used in transformer decoder layer?

Open

#537 opened on Feb 27, 2019

View on GitHub
 (1 comment) (0 reactions) (0 assignees)Python (6,224 forks)batch import
bughelp wanted

Repository metrics

Stars
 (29,107 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

when reading the source code i found that key_padding_mask is not used when calculating self attention. There is no problem when the target is padded right by default because attn_mask could do the same thing. But how about left padding on the target?

Contributor guide

Research direction
Examine the transformer decoder layer source code to verify if key padding mask is ignored in self attention; then propose a patch to incorporate it, considering left padded targets.
Tech stack
python
Domain
backendmachine learning
Issue type
Bug
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.
1-3 hours
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.
Needs investigation
Prerequisites
PythonPyTorchTransformer architecture
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
45