How to extract entities from text using Wikipedia2Vec

[iknoorjobs]

Is there any way I can know the vocabulary of the pretrained model? Like in case of Word2Vec.

[ikuyamada]

You can obtain the list of entities by calling entities() method of the dictionary instance.

from wikipedia2vec import Wikipedia2Vec
model = Wikipedia2Vec.load(MODEL_FILE)
list(model.dictionary.entities())

[iknoorjobs]

Okay, thanks a lot.
And is there any way to extract entities from a paragraph of text?

[ikuyamada]

Wikipedia2Vec does not currently provide a model to extract entities. You need to build a model based on the embeddings.