nmrksic / counter-fitting

Counter-fitting Word Vectors to Linguistic Constraints
Apache License 2.0
145 stars 28 forks source link

Performance on larger vocabulary #2

Open ml-pickle opened 6 years ago

ml-pickle commented 6 years ago

First, thanks so much for posting your code!

Counter-fitting glove vectors with a much larger vocab (~2 million words) the number of required dot products for computing VSP pairs obviously explodes (2m^2 vs 50k^2). The included pruned vocab of 50k only takes ~1min on a 4 core machine. What type of time frame did your full glove vocab take? I feel like I must be missing something.

Thanks again Nikola!

natny commented 6 years ago

Hi have you tried this on a larger vocab? Any thoughts?