Veton Matoshi
@MatoshiVeton
Followers
12
Following
36
Media
0
Statuses
4
Joined July 2014
@LukeGessler @ZhiyingJ Digging a bit deeper into the "GZIP beats BERT" paper, I think that a large part of why it works is because it compares character n-grams between documents. You can use this to make the implementation O(n) instead of O(n^2). Here's a write-up:
towardsdatascience.com
A more efficient implementation of compression-based topic classification
1
4
14
🤦♂️
0
0
0
