basaldella / deepkeyphraseextraction Goto Github PK

Hey,
I see in the code that for evaluating INSPEC dataset, only uncontrolled keyphrases are used, but in this comment it says ".contr and .uncontr". What is the source of truth for achieving 0.422 F1@10 score that is mentioned in the Experimental Results section of the paper Bidirectional LSTM Recurrent Neural Network for Keyphrase Extraction?
Thanks in advance!
Laura

ValueError: could not broadcast input array from shape (100) into shape (300)

I'm running a file SimpleRNN.ipynb in Anaconda which is reporting above error on

--- preprocessing.py file
451 if embedding_vector is not None:
452 # words not found in embedding index will be all-zeros.
--> 453 embedding_matrix[i] = embedding_vector
454
455 return train_x, train_y, test_x, test_y, val_x, val_y, embedding_matrix

I am getting the following error.
Please suggest the solution