whoisjones/multinerd

---
dataset_info:
features:
- name: tokens
list: string
- name: text
dtype: string
- name: token_spans
list:
- name: end
dtype: int64
- name: label
dtype: string
- name: start
dtype: int64
- name: char_spans
list:
- name: end
dtype: int64
- name: label
dtype: string
- name: start
dtype: int64
splits:
- name: zho_train
num_bytes: 55708434
num_examples: 156160
- name: zho_dev
num_bytes: 6235381
num_examples: 19520
- name: zho_test
num_bytes: 6905032
num_examples: 19577
- name: fra_train
num_bytes: 60428639
num_examples: 140880
- name: fra_dev
num_bytes: 8223541
num_examples: 17610
- name: fra_test
num_bytes: 8232944
num_examples: 17695
- name: pol_train
num_bytes: 52935497
num_examples: 155920
- name: pol_dev
num_bytes: 6864303
num_examples: 19490
- name: pol_test
num_bytes: 6632425
num_examples: 19555
- name: por_train
num_bytes: 60165651
num_examples: 142000
- name: por_dev
num_bytes: 7190375
num_examples: 17750
- name: por_test
num_bytes: 7063228
num_examples: 17815
- name: deu_train
num_bytes: 45376438
num_examples: 125360
- name: deu_dev
num_bytes: 5804280
num_examples: 15670
- name: deu_test
num_bytes: 5862923
num_examples: 15762
- name: nld_train
num_bytes: 47863842
num_examples: 137360
- name: nld_dev
num_bytes: 6155986
num_examples: 17170
- name: nld_test
num_bytes: 6057184
num_examples: 17181
- name: eng_train
num_bytes: 52099227
num_examples: 131280
- name: eng_dev
num_bytes: 6934356
num_examples: 16410
- name: eng_test
num_bytes: 6449456
num_examples: 16454
- name: ita_train
num_bytes: 69775167
num_examples: 145520
- name: ita_dev
num_bytes: 8842769
num_examples: 18190
- name: ita_test
num_bytes: 9069586
num_examples: 18217
- name: spa_train
num_bytes: 61954002
num_examples: 138480
- name: spa_dev
num_bytes: 8104668
num_examples: 17310
- name: spa_test
num_bytes: 7890209
num_examples: 17399
- name: rus_train
num_bytes: 33700462
num_examples: 66240
- name: rus_dev
num_bytes: 4089710
num_examples: 8280
- name: rus_test
num_bytes: 4137346
num_examples: 8338
download_size: 278089071
dataset_size: 676753061
configs:
- config_name: zho
data_files:
- split: train
path: data/zho_train*
- split: dev
path: data/zho_dev*
- split: test
path: data/zho_test*
- config_name: fra
data_files:
- split: train
path: data/fra_train*
- split: dev
path: data/fra_dev*
- split: test
path: data/fra_test*
- config_name: pol
data_files:
- split: train
path: data/pol_train*
- split: dev
path: data/pol_dev*
- split: test
path: data/pol_test*
- config_name: por
data_files:
- split: train
path: data/por_train*
- split: dev
path: data/por_dev*
- split: test
path: data/por_test*
- config_name: deu
data_files:
- split: train
path: data/deu_train*
- split: dev
path: data/deu_dev*
- split: test
path: data/deu_test*
- config_name: nld
data_files:
- split: train
path: data/nld_train*
- split: dev
path: data/nld_dev*
- split: test
path: data/nld_test*
- config_name: eng
data_files:
- split: train
path: data/eng_train*
- split: dev
path: data/eng_dev*
- split: test
path: data/eng_test*
- config_name: ita
data_files:
- split: train
path: data/ita_train*
- split: dev
path: data/ita_dev*
- split: test
path: data/ita_test*
- config_name: spa
data_files:
- split: train
path: data/spa_train*
- split: dev
path: data/spa_dev*
- split: test
path: data/spa_test*
- config_name: rus
data_files:
- split: train
path: data/rus_train*
- split: dev
path: data/rus_dev*
- split: test
path: data/rus_test*
---