Implement the truly SOTA aligner - Mask Align
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39
- Forks
- 7
- Avg merge
- 1d 9h
- Merged PRs (30d)
- 5
Description
https://github.com/THUNLP-MT/Mask-Align
No idea how much work this would be, but it appears to outperform Eflomal quite a bit.
Contributor guide
No contributing guide indexed for this repository
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 Mask-Align project and comparing it with this repository’s Eflomal-based alignment work. No local files or tests are named, so first identify the alignment entry point and define whether Mask Align should replace or supplement Eflomal. Done requires a working pipeline integration and evidence from the relevant alignment experiments.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100