asyml / asyml/texar

Gumbel softmax trick with beam search

Open
#209 1 comment 0 reactions 0 assignees View on GitHub
enhancement help wanted topic: modules
Dominant language
Python
Stars
2.4k
Forks
367
PR merge metrics
No merged PRs in 30d

Description

Is it possible to use Gumbel softmax trick with a beam search decoder in the existing implementation of Texar. I want to differentiate through the generated beam search samples into the generator network.

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating Texar's existing beam search decoder and generator interfaces, then review how generated samples are represented during decoding. Determine whether Gumbel-softmax gradients can pass through beam-search samples; done requires a defined implementation path and validation of differentiation into the generator network.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, tensorflow
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.