SyntacticPlusW2VModel

class mowl.models.SyntacticPlusW2VModel(*args, **kwargs)

Bases: SyntacticModel

Model that combines corpus generation with Word2Vec training.

New in version 0.2.0.

Attributes Summary

class_embeddings	Returns a dictionary with class names as keys and class embeddings as values.
individual_embeddings	Returns a dictionary with individual names as keys and individual embeddings as values.
object_property_embeddings	Returns a dictionary with object property names as keys and object property embeddings as values.

Methods Summary

add_axioms(*axioms)	This method adds axioms to the dataset contained in the model and reorders the embedding information for each entity accordingly.
from_pretrained(model)	This method loads a pretrained model from a file.
set_w2v_model(*args, **kwargs)	This method sets the gensim.models.word2vec.Word2Vec model to be used in the syntactic model.
train([epochs])	Triggers the Word2Vec training process.

Attributes Documentation

class_embeddings

individual_embeddings

object_property_embeddings

Methods Documentation

add_axioms(*axioms)

This method adds axioms to the dataset contained in the model and reorders the embedding information for each entity accordingly. New entites are initalized with random embedding.

Parameters:

axioms (org.semanticweb.owlapi.model.OWLAxiom) – Axioms to be added to the dataset.

New in version 0.2.0.

from_pretrained(model)

This method loads a pretrained model from a file.

Parameters:

file_name (str) – Path to the pretrained model file.

New in version 0.2.0.

set_w2v_model(*args, **kwargs)

This method sets the gensim.models.word2vec.Word2Vec model to be used in the syntactic model.

Parameters:

• args – Arguments to be passed to the Word2Vec constructor.

• kwargs – Keyword arguments to be passed to the Word2Vec constructor.

train(epochs=None)

Triggers the Word2Vec training process.

Parameters:

epochs (int) – Number of epochs to train the model. If None, the value of the epochs parameter passed to the constructor will be used.