translate.py 文件源码

def _build_dictionaries(self):
        """
        Builds and inverts source and target dictionaries, taken
        from the first model since all of them must have the same
        vocabulary.
        """
        dictionaries = self._options[0]['dictionaries']
        dictionaries_source = dictionaries[:-1]
        dictionary_target = dictionaries[-1]

        # load and invert source dictionaries
        word_dicts = []
        word_idicts = []
        for dictionary in dictionaries_source:
            word_dict = load_dict(dictionary)
            if self._options[0]['n_words_src']:
                for key, idx in word_dict.items():
                    if idx >= self._options[0]['n_words_src']:
                        del word_dict[key]
            word_idict = dict()
            for kk, vv in word_dict.iteritems():
                word_idict[vv] = kk
            word_idict[0] = '<eos>'
            word_idict[1] = 'UNK'
            word_dicts.append(word_dict)
            word_idicts.append(word_idict)

        self._word_dicts = word_dicts
        self._word_idicts = word_idicts

        # load and invert target dictionary
        word_dict_trg = load_dict(dictionary_target)
        word_idict_trg = dict()
        for kk, vv in word_dict_trg.iteritems():
            word_idict_trg[vv] = kk
        word_idict_trg[0] = '<eos>'
        word_idict_trg[1] = 'UNK'

        self._word_idict_trg = word_idict_trg