LoginSignup
0
0

More than 1 year has passed since last update.

simple BPE

Last updated at Posted at 2021-07-03
import re, collections

def get_stats(vocab):
  pairs = collections.defaultdict(int) 
  for word, freq in vocab.items():
    symbols = word.split()
    for i in range(len(symbols)-1):
      pairs[symbols[i],symbols[i+1]] += freq 

  return pairs

def merge_vocab(pair, v_in):
  v_out = {}
  bigram = re.escape(' '.join(pair))
  p = re.compile(r'(?<!\S)' + bigram + r'(?!\S)') 
  for word in v_in:
    w_out = p.sub(''.join(pair), word)
    v_out[w_out] = v_in[word] 
  return v_out

vocab = {'l o w </w>' : 5, 'l o w e r </w>' : 2, 'n e w e s t </w>':6,'w i d e s t </w>':3}
num_merges = 10
for i in range(num_merges):
  print(i)
  pairs = get_stats(vocab)
  best = max(pairs, key=pairs.get) 
  vocab = merge_vocab(best, vocab) 
  print(best)

print(vocab)

0
0
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
0
0