nlg_tok_int_mapping.py

# create integer-to-token mapping
int2token = {}
cnt = 0

for w in set(" ".join(movie_plots).split()):
  int2token[cnt] = w
  cnt+= 1

# create token-to-integer mapping
token2int = {t: i for i, t in int2token.items()}

token2int["the"], int2token[14271]