def get_all_words(self): """ Return all words tokenized, in lowercase and without punctuation """ return [w.lower() for w in word_tokenize(self.text) if w not in string.punctuation]
I found that in this function, only punctuation of the text was removed. But there are other types of words that have not been removed.
eg:
`from nltk.corpus import stopwords

I have trained almost 80thousand examples within 2000 labels，valid acc almost 92%，but test result all example prob is blew 0.01.
I have tried tranning examples to predict.