Creation of sequential embeddings
Opened this issue · 2 comments
I am trying to repeat the experiment but using a different dataset. I was able to prepare the data in the preprocessing files, but I am having trouble creating sequential embeddings from rank_lstm.py to use in relation_rank_lstm.py. How did you save the hidden state of the LSTM in the correct format?
According to the released sequential embeddings and the default parameters, it should be easy to figure out the correct dimensions.
I'm lost as to how I can generate the sequential embeddings. Can anyone of you guide me or give some general tips as to how to accomplish this?
Like the OP, I've successfully preprocessed my data by modifying the eod.py file, but after that, I just don't know how to generate the sequential embedding files.