huggingface / huggingface/neuralcoref
How to retrain neuralcoref using ELMo?
Open
wontfix
- Dominant language
- C
- Stars
- 2.9k
- Forks
- 467
- PR merge metrics
- No merged PRs in 30d
Description
neuralcoref works well for majority of our use cases, but we're trying to eek out whatever remaining bits of performance we could. I noticed in https://github.com/huggingface/neuralcoref/blob/master/neuralcoref/train/training.md there is a reference for using ELMo word vectors
Wondering where we would go in the code to implement that or if the spacy v3 upgrade plans for neuralcoref include newer embeddings?
Thanks!
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.