Constrained beam search like Fairseq
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 4.7k
- Forks
- 537
- Avg merge
- 12h 12m
- Merged PRs (30d)
- 4
Description
Hi, can someone help, how to get started with implementing unordered constrained beam search from Fairseq.
https://github.com/facebookresearch/fairseq/blob/main/examples/constrained_decoding/README.md
What part of decoding code should I tweak, what are the important steps in decoding?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked Fairseq constrained decoding README and locating the CTranslate2 decoding code referred to in the issue. The issue does not name a file or test; done would require implementing unordered constrained beam search with behavior aligned to the Fairseq approach and establishing how it should be verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100