Kernel crashes when trying to run demo code

I've tried running the demo code from the repo readme:

```
# Load your usual SpaCy model (one of SpaCy English models)
import spacy
nlp = spacy.load('en')

# Add neural coref to SpaCy's pipe
import neuralcoref
neuralcoref.add_to_pipe(nlp)

# You're done. You can now use NeuralCoref as you usually manipulate a SpaCy document annotations.
doc = nlp(u'My sister has a dog. She loves him.')

doc._.has_coref
doc._.coref_clusters
```

Through commenting out some parts I found that `neuralcoref.add_to_pipe(nlp)` causes the kernel crash.

I'm running on a python 3.8 version which only runs on the dependencies given through `pip install neuralcoref`.
I downgraded the SpaCy version to `2.3.9` as per https://github.com/huggingface/neuralcoref/issues/355#issuecomment-1646816583