-
Notifications
You must be signed in to change notification settings - Fork 14
Open
Description
Was wondering if get_tuple_embedding for CTTTupleEmbedding starting on line 271 in tuple_embeddings_model.py should be:
def get_tuple_embedding(self, list_of_tuples):
embedding_matrix = torch.tensor(self.sif_embedding_model.get_tuple_embedding(list_of_tuples)).float()
return self.ctt_model.get_tuple_embedding(embedding_matrix)
Currently, it is like this:
#This function computes the tuple embedding.
# Given a list of strings, it returns a list of tuple embeddings
# each tuple embedding is 1D numpy ndarray
def get_tuple_embedding(self, list_of_tuples):
embedding_matrix = torch.tensor(self.sif_embedding_model.get_tuple_embedding(list_of_tuples)).float()
return embedding_matrix
Metadata
Metadata
Assignees
Labels
No labels