Ejemplo n.º 1
0
           'which will be used for demonstration purpose.')
    unofficial_chinese = get_resource('https://github.com/GuocaiL/Coref_Resolution/archive/master.zip#data/')
    intended_home, _ = os.path.splitext(intended_file_path)
    intended_chinese = f'{intended_home}/data/files/data/chinese/'
    # print(os.path.dirname(intended_chinese))
    # print(unofficial_chinese)
    # print(intended_chinese)
    for folder in ['annotations', 'metadata']:
        flash(f'Copying {unofficial_chinese}{folder} to {intended_chinese}{folder} [blink][yellow]...[/yellow][/blink]')
        shutil.copytree(f'{unofficial_chinese}{folder}', f'{intended_chinese}{folder}')
    flash('')

try:
    get_resource(ONTONOTES5_CONLL12_CHINESE_TRAIN, verbose=False)
except HTTPError:
    make_gold_conll(ONTONOTES5_HOME + '..', 'chinese')
    make_ontonotes_language_jsonlines(CONLL12_HOME + 'v4', language='chinese')

batch_make_ner_tsv_if_necessary(
    [ONTONOTES5_CONLL12_CHINESE_TRAIN, ONTONOTES5_CONLL12_CHINESE_DEV, ONTONOTES5_CONLL12_CHINESE_TEST])

batch_make_ner_tsv_if_necessary(
    [ONTONOTES5_CONLL12_CHINESE_TRAIN, ONTONOTES5_CONLL12_CHINESE_DEV, ONTONOTES5_CONLL12_CHINESE_TEST])

batch_make_ner_tsv_if_necessary(
    [ONTONOTES5_CHINESE_TRAIN, ONTONOTES5_CHINESE_DEV, ONTONOTES5_CHINESE_TEST])

batch_make_pos_tsv_if_necessary(
    [ONTONOTES5_CHINESE_TRAIN, ONTONOTES5_CHINESE_DEV, ONTONOTES5_CHINESE_TEST])

batch_make_con_txt_if_necessary(
Ejemplo n.º 2
0
ONTONOTES5_NER_ENGLISH_TEST = _ONTONOTES5_CONLL12_ENGLISH_HOME + 'test.english.v4.ner.tsv'

try:
    get_resource(ONTONOTES5_HOME, verbose=False)
except HTTPError:
    intended_file_path = path_from_url(ONTONOTES5_HOME)
    cprint(
        'Ontonotes 5.0 is a [red][bold]copyright[/bold][/red] dataset owned by LDC which we cannot re-distribute. '
        f'Please apply for a licence from LDC (https://catalog.ldc.upenn.edu/LDC2016T13) '
        f'then download it to {intended_file_path}')
    exit(1)

try:
    get_resource(ONTONOTES5_CONLL12_ENGLISH_TRAIN, verbose=False)
except HTTPError:
    make_gold_conll(ONTONOTES5_HOME + '..', 'english')
    make_ontonotes_language_jsonlines(CONLL12_HOME + 'v4', language='english')

batch_make_ner_tsv_if_necessary([
    ONTONOTES5_CONLL12_ENGLISH_TRAIN, ONTONOTES5_CONLL12_ENGLISH_DEV,
    ONTONOTES5_CONLL12_ENGLISH_TEST
])

batch_make_ner_tsv_if_necessary([
    ONTONOTES5_ENGLISH_TRAIN, ONTONOTES5_ENGLISH_DEV, ONTONOTES5_ENGLISH_TEST
])

batch_make_pos_tsv_if_necessary([
    ONTONOTES5_ENGLISH_TRAIN, ONTONOTES5_ENGLISH_DEV, ONTONOTES5_ENGLISH_TEST
])