NT drafting support
Nobody has claimed this yet.
- Dominant language
- C#
- Stars
- 3
- Forks
- 2
- Avg merge
- 3d 1h
- Merged PRs (30d)
- 3
Description
In order to support the new NT drafting features in Scripture Forge, Serval needs to primary features: chapter-level filtering for training/inferencing and model confidence scores. Serval should already mostly support chapter-level filtering. There is a known issue that needs to be fixed for it to work properly with the way that Scripture Forge configures engines. Serval will also need to be able to return the model confidence score for a pretranslation. The confidence scores will be used to compute a usability score for display to users. An implementation of this algorithm will be provided in the Machine library, so that it can be shared across silnlp and Scripture Forge.
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
Review Serval's existing chapter-level filtering and the engine configuration path, then inspect how pretranslation responses expose model data. Done means filtering works with Scripture Forge-configured engines and confidence scores are returned for the Machine library's usability scoring.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- csharp
- Domain
- api, backend, machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100