neuralcoref VS ML-Workspace

Training instructions: https://github.com/huggingface/neuralcoref/blob/master/neuralcoref/train/training.md

Besides that, you may also try searching for your problem on GitHub Issues, or create an issue yourself if you can't find an existing one.

I guess you have tried neuralcoref already https://github.com/huggingface/neuralcoref ?

Hi. Let me elaborate on the title. I'm currently working on paragraph-level data and want to perform coreference resolution. I've tried working with spaCy's NeuralCoref, and although it works great it receives a string as input and returns all entities and mentions it deems appropriate. Rather than that I'm looking for something where you can specify the entity and the model will return all such instances for that particular entity.

Also check out: https://github.com/ml-tooling/ml-workspace, it a nice open source project with lots of packages ready to use.

The other option - no reason why you couldn't host something on the desktop machine - web based IDE like R-Studio or Python - have a look at ml-workspace - https://github.com/ml-tooling/ml-workspace that runs in Docker and would provide interfaces for both Python and R, VSCode as well as a GPU accelerated variant for doing Tensorflow etc - either Windows or Linux can support Docker containers (Linux is less trouble apparently - I only have played with it in Linux personally)

It will be a web based IDE dev kit (like Jupyter Hub, or JupyterLab) if you are familiar with them)

I'll stick with https://github.com/ml-tooling/ml-workspace, is a docker with all tools installed, also the option of using GPU, so I think is better than only for debian. This way anyone can use it.