sillsdev / sillsdev/silnlp

Convert less common scripts to Latin, Arabic, cyrilic

Open
#293 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

research
Dominant language
Python
Stars
39
Forks
7
Avg merge
1d 9h
Merged PRs (30d)
5

Description

There is great research from Taeho Jang that we could get a 10pnt Bleu score bump from using a common script instead of an uncommon one. This should be aggressively researched. A possible implementation:

  • Find a good tokenizer (TECkit) to convert to a common script
  • Run the NLLB model
  • Reconvert to the original script (either with TECkit or training a model in both directions)

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Read the linked Taeho Jang research and the proposed TECkit → NLLB → reconversion workflow first. Done should be demonstrated by a reproducible experiment showing the claimed BLEU improvement while preserving the original script.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
internationalization, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.