Model does not create the topic embedding representation

[un-lock-me]

Hi,

I tried to visualize the output of your work, sadly it does not work as it needs the embedding file for the visualization, In none of the steps this file is being created,

exactly this line in save_embeds.py : feed_dict = {embed_vals: np.load(f_embed)}

I dont have the f_embed to pass,

May I have your view on this? thanks

[nateraw]

It seems other people, including myself, are also experiencing your issue of the topic/document embeddings not training properly. As for your other issue...

Take a look at these 2 links to Chris Moody's repository. He doesn't name it f_embed, but it is the same variable I believe.

https://github.com/cemoody/lda2vec/blob/master/examples/twenty_newsgroups/data/preprocess.py

https://github.com/cemoody/lda2vec/blob/master/lda2vec/corpus.py

In preprocess.py, we see he passes google news embeddings to a function to return the pretrained embeddings.

By googling 'GoogleNews-vectors-negative300.bin' you can find a place to download it.