How to use the tokenizers.NLTKTokenizer function in tokenizers

To help you get started, we’ve selected a few tokenizers examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github singletongue / WikiEntVec / tokenizers.py View on Github external
def __init__(self, lower=False):
        super(NLTKTokenizer, self).__init__(lower)
        from nltk import word_tokenize
        self.word_tokenize = word_tokenize
github singletongue / WikiEntVec / generate_corpus.py View on Github external
default='regexp',
                        help='type of tokenizer [regexp]')
    parser.add_argument('--lower', action='store_true',
                        help='lowercase words (not applied to NEs)')
    parser.add_argument('--mecab_dic', type=str, default=None,
                        help='dictionary for MeCab tokenizer')
    parser.add_argument('--mecab_udic', type=str, default=None,
                        help='user dictionary for MeCab tokenizer')
    args = parser.parse_args()

    if args.tokenizer == 'regexp':
        logging.info('tokenizer: RegExpTokenizer')
        tokenizer = tokenizers.RegExpTokenizer(lower=args.lower)
    elif args.tokenizer == 'nltk':
        logging.info('tokenizer: NLTKTokenizer')
        tokenizer = tokenizers.NLTKTokenizer(lower=args.lower)
    elif args.tokenizer == 'mecab':
        logging.info('tokenizer: MeCabTokenizer')
        logging.info(f'dictionary: {args.mecab_dic}')
        logging.info(f'user dictionary: {args.mecab_udic}')
        tokenizer = tokenizers.MeCabTokenizer(
            dic=args.mecab_dic, udic=args.mecab_udic, lower=args.lower)
    else:
        raise Exception('Undefined tokenizer type.')

    logging.info('generating corpus for training')
    n_processed = 0
    with gzip.open(args.cirrus_file, 'rt') as fi, \
         bz2.open(args.out_file, 'wt') as fo:
        for line in fi:
            article = json.loads(line)
            if 'title' not in article: