How to retrain neuralcoref using ELMo?

[Hevia]

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!

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.