Method tokenize

official/nlp/tools/tokenization.py:207–232

Tokenizes a piece of text.

(self, text)

    self.split_on_punc = split_on_punc

  def tokenize(self, text):
    """Tokenizes a piece of text."""
    text = convert_to_unicode(text)
    text = self._clean_text(text)

    # This was added on November 1st, 2018 for the multilingual and Chinese
    # models. This is also applied to the English models now, but it doesn't
    # matter since the English models were not trained on any Chinese data
    # and generally don't have any Chinese data in them (there are Chinese
    # characters in the vocabulary because Wikipedia does have some Chinese
    # words in the English Wikipedia.).
    text = self._tokenize_chinese_chars(text)

    orig_tokens = whitespace_tokenize(text)
    split_tokens = []
    for token in orig_tokens:
      if self.do_lower_case:
        token = token.lower()
        token = self._run_strip_accents(token)
      if self.split_on_punc:
        split_tokens.extend(self._run_split_on_punc(token))
      else:
        split_tokens.append(token)

    output_tokens = whitespace_tokenize(" ".join(split_tokens))
    return output_tokens

  def _run_strip_accents(self, text):
    """Strips accents from a piece of text."""