lucy3 / grounding-embeddings Goto Github PK

Hi Lucy and Jon,

Thank you for such a thoughtful, precise, and motivating paper, and for sharing your code!

I have a humble request, which I will take no offence if you ignore: might you provide a script to gather the data this code requires, and instructions for getting the data that isn't script get-able (which appears to be because (an) agreement(s) must be signed)?

Warm regards,
Max

Hi,

Thanks for sharing your code. I was not sure what format the vocab.txt should be, as the file was not in the repo, so I tested the code with a vocab.txt with single words on each line. Example:

yellow
woods
hanging
regularize

But, even with a very small vocab file of 53 words, the script ends up using too much memory (order of 200GB RAM) and gets killed in some time during, '$(datadir)/cooccurrence.filtered.bin: filter_glove' step in the Makefile. Am I running the script with the right input? (there are no other errors reported)