In the chapter 10_NLP, I try my data into DBPEDIA, but i got stuck on numericalization issue which I always got 0.
token.setup(text_list)
toks = token(text_list)
print(coll_repr(token
(text_list[0]), 31))
toks200 = sample_text[:200].map(token)
toks200[0]
num = Numericalize()
num.setup(toks200)
coll_repr(num.vocab,20)
nums = num(toks)[:50]
nums
TensorText([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
i don’t know how to fix this.