jonathanbratt / jonathanbratt/RBERT
step_rbert_features
Open
enhancement
- Dominant language
- R
- Stars
- 166
- Forks
- 19
- PR merge metrics
- No merged PRs in 30d
Description
I'm not sure yet if this should be inside RBERT or maybe integrated into [tidymodels/textrecipes](github.com/tidymodels/textrecipes), but we should make it easy to extract features from text in some sort of standard form using BERT checkpoints (within a recipes pipeline).
Contributor guide
Research direction
Start by determining whether this belongs in RBERT or tidymodels/textrecipes, then define the standard feature representation and how it fits into a recipes pipeline. Done means the integration location, BERT checkpoint handling, and expected extracted features are specified clearly enough to implement.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- r, tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100