ellamind/wikipedia-2023-11-retrieval-multilingual-corpus

---
dataset_info:
- config_name: bg
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 9681710
num_examples: 13500
download_size: 4633852
dataset_size: 9681710
- config_name: bn
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 14694766
num_examples: 13500
download_size: 5529387
dataset_size: 14694766
- config_name: cs
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 6094140
num_examples: 13500
download_size: 3950951
dataset_size: 6094140
- config_name: da
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5321047
num_examples: 13500
download_size: 3212721
dataset_size: 5321047
- config_name: de
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 6062342
num_examples: 13500
download_size: 3637796
dataset_size: 6062342
- config_name: en
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 6677737
num_examples: 13500
download_size: 3998998
dataset_size: 6677737
- config_name: fa
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 9038000
num_examples: 13500
download_size: 4263332
dataset_size: 9038000
- config_name: fi
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5885015
num_examples: 13500
download_size: 3532409
dataset_size: 5885015
- config_name: hi
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 14879843
num_examples: 13500
download_size: 5629118
dataset_size: 14879843
- config_name: it
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5905698
num_examples: 13500
download_size: 3604209
dataset_size: 5905698
- config_name: nl
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5647998
num_examples: 13500
download_size: 3295722
dataset_size: 5647998
- config_name: 'no'
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5616224
num_examples: 13500
download_size: 3406110
dataset_size: 5616224
- config_name: pt
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 6080375
num_examples: 13500
download_size: 3690233
dataset_size: 6080375
- config_name: ro
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5482624
num_examples: 13500
download_size: 3346015
dataset_size: 5482624
- config_name: sr
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 9445283
num_examples: 13500
download_size: 4775552
dataset_size: 9445283
- config_name: sv
features:
- name: _id
dtype: string
- name: title
dtype: string
- name: text
dtype: string
splits:
- name: test
num_bytes: 5741282
num_examples: 13500
download_size: 3424342
dataset_size: 5741282
configs:
- config_name: bg
data_files:
- split: test
path: bg/test-*
- config_name: bn
data_files:
- split: test
path: bn/test-*
- config_name: cs
data_files:
- split: test
path: cs/test-*
- config_name: da
data_files:
- split: test
path: da/test-*
- config_name: de
data_files:
- split: test
path: de/test-*
- config_name: en
data_files:
- split: test
path: en/test-*
- config_name: fa
data_files:
- split: test
path: fa/test-*
- config_name: fi
data_files:
- split: test
path: fi/test-*
- config_name: hi
data_files:
- split: test
path: hi/test-*
- config_name: it
data_files:
- split: test
path: it/test-*
- config_name: nl
data_files:
- split: test
path: nl/test-*
- config_name: 'no'
data_files:
- split: test
path: no/test-*
- config_name: pt
data_files:
- split: test
path: pt/test-*
- config_name: ro
data_files:
- split: test
path: ro/test-*
- config_name: sr
data_files:
- split: test
path: sr/test-*
- config_name: sv
data_files:
- split: test
path: sv/test-*
---

原始信息汇总

数据集概述

数据集配置信息

配置名称	特征	分割	字节数	示例数	下载大小	数据集大小
bg	_id: string, title: string, text: string	test	9681710	13500	4633852	9681710
bn	_id: string, title: string, text: string	test	14694766	13500	5529387	14694766
cs	_id: string, title: string, text: string	test	6094140	13500	3950951	6094140
da	_id: string, title: string, text: string	test	5321047	13500	3212721	5321047
de	_id: string, title: string, text: string	test	6062342	13500	3637796	6062342
en	_id: string, title: string, text: string	test	6677737	13500	3998998	6677737
fa	_id: string, title: string, text: string	test	9038000	13500	4263332	9038000
fi	_id: string, title: string, text: string	test	5885015	13500	3532409	5885015
hi	_id: string, title: string, text: string	test	14879843	13500	5629118	14879843
it	_id: string, title: string, text: string	test	5905698	13500	3604209	5905698
nl	_id: string, title: string, text: string	test	5647998	13500	3295722	5647998
no	_id: string, title: string, text: string	test	5616224	13500	3406110	5616224
pt	_id: string, title: string, text: string	test	6080375	13500	3690233	6080375
ro	_id: string, title: string, text: string	test	5482624	13500	3346015	5482624
sr	_id: string, title: string, text: string	test	9445283	13500	4775552	9445283
sv	_id: string, title: string, text: string	test	5741282	13500	3424342	5741282

数据文件路径

配置名称	分割	路径
bg	test	bg/test-*
bn	test	bn/test-*
cs	test	cs/test-*
da	test	da/test-*
de	test	de/test-*
en	test	en/test-*
fa	test	fa/test-*
fi	test	fi/test-*
hi	test	hi/test-*
it	test	it/test-*
nl	test	nl/test-*
no	test	no/test-*
pt	test	pt/test-*
ro	test	ro/test-*
sr	test	sr/test-*
sv	test	sv/test-*