sillsdev / sillsdev/silnlp

Verse segmentation - when confidence scores are low, combine two verses into a verse range.

Open
#916 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement pipeline 3: preprocess research
Dominant language
Python
Stars
39
Forks
7
Avg merge
1d 9h
Merged PRs (30d)
5

Description

Improve the verse segmentation algorithm by setting a threshold for quality using alignment scores, and then if the threshold is not met, combining them into a single verse range, rather than trying to split them. We could also use length as an indicator (so a verse range doesn’t get too long for NLLB).

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

No file, test, or entry point is named. Start by locating the verse segmentation algorithm and where alignment scores are calculated, then determine how segmentation thresholds and verse-range length limits are represented. Done means low-confidence segments combine into verse ranges without exceeding the relevant NLLB length constraint, with coverage for the new behavior.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.