def expanded_vector(self, terms, limit_per_term=10, include_neighbors=True):
# TODO: docstring
self.load()
return weighted_average(
self.frame,
self.expand_terms(terms, limit_per_term, include_neighbors)
)
def expanded_vector(self, terms, oov_vector=True):
"""
Given a list of weighted terms as (term, weight) tuples, make a vector
representing information from:
- The vectors for these terms
- The vectors for equivalently spelled terms in the English vocabulary
- The vectors for terms that share a sufficiently-long prefix with
any terms in this list that are out-of-vocabulary
"""
return weighted_average(self.frame,
self.expand_terms(terms, oov_vector))
def expanded_vector(self, terms, limit_per_term=10, oov_vector=True):
"""
Given a list of weighted terms as (term, weight) tuples, make a vector
representing information from:
- The vectors for these terms
- The vectors for their neighbors in ConceptNet
- The vectors for terms that share a sufficiently-long prefix with
any terms in this list that are out-of-vocabulary
"""
self.load()
return weighted_average(
self.frame, self.expand_terms(terms, limit_per_term, oov_vector))
def expanded_vector(self, terms, limit_per_term=10, oov_vector=True):
"""
Given a list of weighted terms as (term, weight) tuples, make a vector
representing information from:
- The vectors for these terms
- The vectors for their neighbors in ConceptNet
- The vectors for terms that share a sufficiently-long prefix with
any terms in this list that are out-of-vocabulary
"""
self.load()
return weighted_average(
self.frame, self.expand_terms(terms, limit_per_term, oov_vector)
)
def expanded_vector(self, terms, limit_per_term=10, include_neighbors=True):
self.load()
return weighted_average(self.frame, self.expand_terms(terms, limit_per_term, include_neighbors))
