pytorch_transformers/tokenization_openai.py [108:184]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {}

    @property
    def vocab_size(self):
        return len(self.encoder)

    def bpe(self, token):
        word = tuple(token[:-1]) + (token[-1] + '</w>',)
        if token in self.cache:
            return self.cache[token]
        pairs = get_pairs(word)

        if not pairs:
            return token+'</w>'

        while True:
            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float('inf')))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                    new_word.extend(word[i:j])
                    i = j
                except:
                    new_word.extend(word[i:])
                    break

                if word[i] == first and i < len(word)-1 and word[i+1] == second:
                    new_word.append(first+second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = ' '.join(word)
        if word == '\n  </w>':
            word = '\n</w>'
        self.cache[token] = word
        return word

    def _tokenize(self, text):
        """ Tokenize a string. """
        split_tokens = []
        if self.fix_text is None:
            # Using BERT's BasicTokenizer
            text = self.nlp.tokenize(text)
            for token in text:
                split_tokens.extend([t for t in self.bpe(token).split(' ')])
        else:
            # Using SpaCy & ftfy (original tokenization process of OpenAI GPT)
            text = self.nlp(text_standardize(self.fix_text(text)))
            for token in text:
                split_tokens.extend([t for t in self.bpe(token.text.lower()).split(' ')])
        return split_tokens

    def _convert_token_to_id(self, token):
        """ Converts a token (str/unicode) in an id using the vocab. """
        return self.encoder.get(token, self.encoder.get(self.unk_token))

    def _convert_id_to_token(self, index):
        """Converts an id in a token (BPE) using the vocab."""
        return self.decoder.get(index, self.unk_token)

    def convert_tokens_to_string(self, tokens):
        """ Converts a sequence of tokens (string) in a single string. """
        out_string = ''.join(tokens).replace('</w>', ' ').strip()
        return out_string
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



pytorch_transformers/tokenization_xlm.py [144:220]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {}

    @property
    def vocab_size(self):
        return len(self.encoder)

    def bpe(self, token):
        word = tuple(token[:-1]) + (token[-1] + '</w>',)
        if token in self.cache:
            return self.cache[token]
        pairs = get_pairs(word)

        if not pairs:
            return token+'</w>'

        while True:
            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float('inf')))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                    new_word.extend(word[i:j])
                    i = j
                except:
                    new_word.extend(word[i:])
                    break

                if word[i] == first and i < len(word)-1 and word[i+1] == second:
                    new_word.append(first+second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = ' '.join(word)
        if word == '\n  </w>':
            word = '\n</w>'
        self.cache[token] = word
        return word

    def _tokenize(self, text):
        """ Tokenize a string. """
        split_tokens = []
        if self.fix_text is None:
            # Using BERT's BasicTokenizer
            text = self.nlp.tokenize(text)
            for token in text:
                split_tokens.extend([t for t in self.bpe(token).split(' ')])
        else:
            # Using SpaCy & ftfy (original tokenization process of OpenAI GPT)
            text = self.nlp(text_standardize(self.fix_text(text)))
            for token in text:
                split_tokens.extend([t for t in self.bpe(token.text.lower()).split(' ')])
        return split_tokens

    def _convert_token_to_id(self, token):
        """ Converts a token (str/unicode) in an id using the vocab. """
        return self.encoder.get(token, self.encoder.get(self.unk_token))

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (string/unicode) using the vocab."""
        return self.decoder.get(index, self.unk_token)

    def convert_tokens_to_string(self, tokens):
        """ Converts a sequence of tokens (string) in a single string. """
        out_string = ''.join(tokens).replace('</w>', ' ').strip()
        return out_string
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -