en_coref_lg model in spacy

Question

Hi I am trying a simple coref resolution code in python as

import spacy
nlp = spacy.load('en_coref_md')
doc = nlp(u'Phone area code will be valid only when all the below conditions are met. It cannot be left blank. It should be numeric. It cannot be less than 200. Minimum number of digits should be 3. ')
print(doc._.coref_clusters)
print(doc._.coref_resolved)

It shows following error:

"OSError: [E050] Can't find model 'en_coref_lg'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data"

If I try to install en_coref_lg using python -m spacy download en_coref_lg then it shows

"✘ No compatible model found for 'en_coref_lg' (spaCy v2.3.2)."

What should I do ?

Answer 1

Install neuralcoref and spacy==2.1.0:

pip uninstall spacy 
pip uninstall neuralcoref
pip install spacy==2.1.0 
pip install neuralcoref --no-binary neuralcoref

Run your code:

import spacy
import neuralcoref
nlp = spacy.load('en_core_web_md')
neuralcoref.add_to_pipe(nlp)
doc = nlp(u'Phone area code will be valid only when all the below conditions are met. It cannot be left blank. It should be numeric. It cannot be less than 200. Minimum number of digits should be 3.')
print(doc._.has_coref)
print(doc._.coref_clusters)
True
[Phone area code: [Phone area code, It, It, It]]

Note the version of spacy==2.1.0. It's required if you want to install with pip.

Alternatively, build from source:

git clone https://github.com/huggingface/neuralcoref.git
cd neuralcoref
pip install -r requirements.txt # check for the desired spacy version
python setup.py install

Proof:

import spacy
import neuralcoref
nlp = spacy.load('en_core_web_md')
neuralcoref.add_to_pipe(nlp)
print(spacy.__version__)
doc = nlp(u'Phone area code will be valid only when all the below conditions are met. It cannot be left blank. It should be numeric. It cannot be less than 200. Minimum number of digits should be 3.')
print(doc._.has_coref)
print(doc._.coref_clusters)
2.3.2
True
[Phone area code: [Phone area code, It, It, It]]

Answer 2

Try to use it like :

import en_coref_md
nllp=en_coref_md.load()

i think it should works.