Skip to content
This repository was archived by the owner on Dec 15, 2024. It is now read-only.

Commit b41750c

Browse files
moriokamorioka
committed
apply json-formatting
1 parent c30e297 commit b41750c

File tree

1 file changed

+185
-1
lines changed

1 file changed

+185
-1
lines changed

‎data/squad_multitask/dataset_infos.json‎

Lines changed: 185 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1 +1,185 @@
1-
{"prepend_qg_format": {"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n", "citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n", "homepage": "https://rajpurkar.github.io/SQuAD-explorer/", "license": "", "features": {"source_text": {"dtype": "string", "id": null, "_type": "Value"}, "target_text": {"dtype": "string", "id": null, "_type": "Value"}, "task": {"dtype": "string", "id": null, "_type": "Value"}}, "supervised_keys": null, "builder_name": "squad_multitask", "config_name": "prepend_qg_format", "version": {"version_str": "1.0.0", "description": "New split API (https://tensorflow.org/datasets/splits)", "nlp_version_to_prepare": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 225952922, "num_examples": 253276, "dataset_name": "squad_multitask"}, "validation": {"name": "validation", "num_bytes": 27650081, "num_examples": 30020, "dataset_name": "squad_multitask"}}, "download_checksums": {"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {"num_bytes": 30288272, "checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"}, "https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {"num_bytes": 4854279, "checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"}}, "download_size": 35142551, "dataset_size": 253603003, "size_in_bytes": 288745554}, "highlight_qg_format": {"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n", "citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n", "homepage": "https://rajpurkar.github.io/SQuAD-explorer/", "license": "", "features": {"source_text": {"dtype": "string", "id": null, "_type": "Value"}, "target_text": {"dtype": "string", "id": null, "_type": "Value"}, "task": {"dtype": "string", "id": null, "_type": "Value"}}, "supervised_keys": null, "builder_name": "squad_multitask", "config_name": "highlight_qg_format", "version": {"version_str": "1.0.0", "description": "New split API (https://tensorflow.org/datasets/splits)", "nlp_version_to_prepare": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 226286197, "num_examples": 253276, "dataset_name": "squad_multitask"}, "validation": {"name": "validation", "num_bytes": 27698388, "num_examples": 30020, "dataset_name": "squad_multitask"}}, "download_checksums": {"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {"num_bytes": 30288272, "checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"}, "https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {"num_bytes": 4854279, "checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"}}, "download_size": 35142551, "dataset_size": 253984585, "size_in_bytes": 289127136}, "prepend_highlight_qg_format": {"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n", "citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n", "homepage": "https://rajpurkar.github.io/SQuAD-explorer/", "license": "", "features": {"source_text": {"dtype": "string", "id": null, "_type": "Value"}, "target_text": {"dtype": "string", "id": null, "_type": "Value"}, "task": {"dtype": "string", "id": null, "_type": "Value"}}, "supervised_keys": null, "builder_name": "squad_multitask", "config_name": "prepend_highlight_qg_format", "version": {"version_str": "1.0.0", "description": "New split API (https://tensorflow.org/datasets/splits)", "nlp_version_to_prepare": null, "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 227967699, "num_examples": 253276, "dataset_name": "squad_multitask"}, "validation": {"name": "validation", "num_bytes": 27893191, "num_examples": 30020, "dataset_name": "squad_multitask"}}, "download_checksums": {"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {"num_bytes": 30288272, "checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"}, "https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {"num_bytes": 4854279, "checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"}}, "download_size": 35142551, "dataset_size": 255860890, "size_in_bytes": 291003441}}
1+
{
2+
"prepend_qg_format": {
3+
"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n",
4+
"citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n",
5+
"homepage": "https://rajpurkar.github.io/SQuAD-explorer/",
6+
"license": "",
7+
"features": {
8+
"source_text": {
9+
"dtype": "string",
10+
"id": null,
11+
"_type": "Value"
12+
},
13+
"target_text": {
14+
"dtype": "string",
15+
"id": null,
16+
"_type": "Value"
17+
},
18+
"task": {
19+
"dtype": "string",
20+
"id": null,
21+
"_type": "Value"
22+
}
23+
},
24+
"supervised_keys": null,
25+
"builder_name": "squad_multitask",
26+
"config_name": "prepend_qg_format",
27+
"version": {
28+
"version_str": "1.0.0",
29+
"description": "New split API (https://tensorflow.org/datasets/splits)",
30+
"nlp_version_to_prepare": null,
31+
"major": 1,
32+
"minor": 0,
33+
"patch": 0
34+
},
35+
"splits": {
36+
"train": {
37+
"name": "train",
38+
"num_bytes": 225952922,
39+
"num_examples": 253276,
40+
"dataset_name": "squad_multitask"
41+
},
42+
"validation": {
43+
"name": "validation",
44+
"num_bytes": 27650081,
45+
"num_examples": 30020,
46+
"dataset_name": "squad_multitask"
47+
}
48+
},
49+
"download_checksums": {
50+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {
51+
"num_bytes": 30288272,
52+
"checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"
53+
},
54+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {
55+
"num_bytes": 4854279,
56+
"checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"
57+
}
58+
},
59+
"download_size": 35142551,
60+
"dataset_size": 253603003,
61+
"size_in_bytes": 288745554
62+
},
63+
"highlight_qg_format": {
64+
"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n",
65+
"citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n",
66+
"homepage": "https://rajpurkar.github.io/SQuAD-explorer/",
67+
"license": "",
68+
"features": {
69+
"source_text": {
70+
"dtype": "string",
71+
"id": null,
72+
"_type": "Value"
73+
},
74+
"target_text": {
75+
"dtype": "string",
76+
"id": null,
77+
"_type": "Value"
78+
},
79+
"task": {
80+
"dtype": "string",
81+
"id": null,
82+
"_type": "Value"
83+
}
84+
},
85+
"supervised_keys": null,
86+
"builder_name": "squad_multitask",
87+
"config_name": "highlight_qg_format",
88+
"version": {
89+
"version_str": "1.0.0",
90+
"description": "New split API (https://tensorflow.org/datasets/splits)",
91+
"nlp_version_to_prepare": null,
92+
"major": 1,
93+
"minor": 0,
94+
"patch": 0
95+
},
96+
"splits": {
97+
"train": {
98+
"name": "train",
99+
"num_bytes": 226286197,
100+
"num_examples": 253276,
101+
"dataset_name": "squad_multitask"
102+
},
103+
"validation": {
104+
"name": "validation",
105+
"num_bytes": 27698388,
106+
"num_examples": 30020,
107+
"dataset_name": "squad_multitask"
108+
}
109+
},
110+
"download_checksums": {
111+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {
112+
"num_bytes": 30288272,
113+
"checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"
114+
},
115+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {
116+
"num_bytes": 4854279,
117+
"checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"
118+
}
119+
},
120+
"download_size": 35142551,
121+
"dataset_size": 253984585,
122+
"size_in_bytes": 289127136
123+
},
124+
"prepend_highlight_qg_format": {
125+
"description": "Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.\n",
126+
"citation": "@article{2016arXiv160605250R,\n author = {{Rajpurkar}, Pranav and {Zhang}, Jian and {Lopyrev},\n Konstantin and {Liang}, Percy},\n title = \"{SQuAD: 100,000+ Questions for Machine Comprehension of Text}\",\n journal = {arXiv e-prints},\n year = 2016,\n eid = {arXiv:1606.05250},\n pages = {arXiv:1606.05250},\narchivePrefix = {arXiv},\n eprint = {1606.05250},\n}\n",
127+
"homepage": "https://rajpurkar.github.io/SQuAD-explorer/",
128+
"license": "",
129+
"features": {
130+
"source_text": {
131+
"dtype": "string",
132+
"id": null,
133+
"_type": "Value"
134+
},
135+
"target_text": {
136+
"dtype": "string",
137+
"id": null,
138+
"_type": "Value"
139+
},
140+
"task": {
141+
"dtype": "string",
142+
"id": null,
143+
"_type": "Value"
144+
}
145+
},
146+
"supervised_keys": null,
147+
"builder_name": "squad_multitask",
148+
"config_name": "prepend_highlight_qg_format",
149+
"version": {
150+
"version_str": "1.0.0",
151+
"description": "New split API (https://tensorflow.org/datasets/splits)",
152+
"nlp_version_to_prepare": null,
153+
"major": 1,
154+
"minor": 0,
155+
"patch": 0
156+
},
157+
"splits": {
158+
"train": {
159+
"name": "train",
160+
"num_bytes": 227967699,
161+
"num_examples": 253276,
162+
"dataset_name": "squad_multitask"
163+
},
164+
"validation": {
165+
"name": "validation",
166+
"num_bytes": 27893191,
167+
"num_examples": 30020,
168+
"dataset_name": "squad_multitask"
169+
}
170+
},
171+
"download_checksums": {
172+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json": {
173+
"num_bytes": 30288272,
174+
"checksum": "3527663986b8295af4f7fcdff1ba1ff3f72d07d61a20f487cb238a6ef92fd955"
175+
},
176+
"https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json": {
177+
"num_bytes": 4854279,
178+
"checksum": "95aa6a52d5d6a735563366753ca50492a658031da74f301ac5238b03966972c9"
179+
}
180+
},
181+
"download_size": 35142551,
182+
"dataset_size": 255860890,
183+
"size_in_bytes": 291003441
184+
}
185+
}

0 commit comments

Comments
 (0)