Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "Jennifer D\u2019Souza; Anett Hoppe; Arthur Brack; Mohamad 
2
  "author": "Jennifer D\u2019Souza; Anett Hoppe; Arthur Brack; Mohamad 
            
3
Yaser Jaradeh; Soren Auer; Ralph Ewerth",
3
Yaser Jaradeh; Soren Auer; Ralph Ewerth",
            
4
  "author_email": "jennifer.dsouza@tib.eu",
4
  "author_email": "jennifer.dsouza@tib.eu",
            
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
6
  "doi": "10.25835/0017546",
6
  "doi": "10.25835/0017546",
            
7
  "doi_date_published": "2020-02-13",
7
  "doi_date_published": "2020-02-13",
            
8
  "doi_publisher": "LUIS",
8
  "doi_publisher": "LUIS",
            
9
  "doi_status": "true",
9
  "doi_status": "true",
            
10
  "domain": "https://data.uni-hannover.de",
10
  "domain": "https://data.uni-hannover.de",
            
11
  "groups": [],
11
  "groups": [],
            
12
  "have_copyright": "Yes",
12
  "have_copyright": "Yes",
            
13
  "id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
13
  "id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
14
  "isopen": false,
14
  "isopen": false,
            
15
  "license_id": "CC-BY-SA-3.0",
15
  "license_id": "CC-BY-SA-3.0",
            
16
  "license_title": "CC-BY-SA-3.0",
16
  "license_title": "CC-BY-SA-3.0",
            
17
  "maintainer": "Jennifer D'Souza",
17
  "maintainer": "Jennifer D'Souza",
            
18
  "maintainer_email": "jennifer.dsouza@tib.eu",
18
  "maintainer_email": "jennifer.dsouza@tib.eu",
            
19
  "metadata_created": "2021-10-14T10:16:07.262891",
19
  "metadata_created": "2021-10-14T10:16:07.262891",
            
n
20
  "metadata_modified": "2021-10-14T10:16:07.262896",
n
20
  "metadata_modified": "2023-01-12T13:14:26.246076",
            
21
  "name": "luh-stem-ecr-v1-0",
21
  "name": "luh-stem-ecr-v1-0",
            
22
  "notes": "##Grounding Scientific Entity References in STEM Scholarly 
22
  "notes": "##Grounding Scientific Entity References in STEM Scholarly 
            
23
Content to Authoritative Encyclopedic and Lexicographic 
23
Content to Authoritative Encyclopedic and Lexicographic 
            
24
Sources\r\n\r\nThe STEM ECR v1.0 dataset has been developed to provide 
24
Sources\r\n\r\nThe STEM ECR v1.0 dataset has been developed to provide 
            
25
a benchmark for the evaluation of scientific entity extraction, 
25
a benchmark for the evaluation of scientific entity extraction, 
            
26
classification, and resolution tasks in a domain-independent fashion. 
26
classification, and resolution tasks in a domain-independent fashion. 
            
27
It comprises annotations for scientific entities in scientific 
27
It comprises annotations for scientific entities in scientific 
            
28
Abstracts drawn from 10 disciplines in Science, Technology, 
28
Abstracts drawn from 10 disciplines in Science, Technology, 
            
29
Engineering, and Medicine. The annotated entities are further grounded 
29
Engineering, and Medicine. The annotated entities are further grounded 
            
30
to Wikipedia and Wiktionary, respectively.\r\n\r\n###What this 
30
to Wikipedia and Wiktionary, respectively.\r\n\r\n###What this 
            
31
repository contains?\r\nThe dataset is organized in the following 
31
repository contains?\r\nThe dataset is organized in the following 
            
32
folders:\r\n\r\n* Scientific Entity Annotations: Contains annotations 
32
folders:\r\n\r\n* Scientific Entity Annotations: Contains annotations 
            
33
for Process, Material, Method, and Data scientific entities in the 
33
for Process, Material, Method, and Data scientific entities in the 
            
34
STEM dataset.\r\n* Scientific Entity Resolution: Annotations for the 
34
STEM dataset.\r\n* Scientific Entity Resolution: Annotations for the 
            
35
STEM dataset scientific entities with Entity Linking (EL) annotations 
35
STEM dataset scientific entities with Entity Linking (EL) annotations 
            
36
to Wikipedia and Word Sense Disambiguation (WSD) annotations to 
36
to Wikipedia and Word Sense Disambiguation (WSD) annotations to 
            
37
Wiktionary.\r\n\r\n\r\n###Annotation Guidelines\r\n\r\nThe annotation 
37
Wiktionary.\r\n\r\n\r\n###Annotation Guidelines\r\n\r\nThe annotation 
            
38
guidelines that supported the creation of this corpus can be found 
38
guidelines that supported the creation of this corpus can be found 
            
39
ter/STEM-ECR-v1.0/annotation-guidelines-for-scientific-linked-data.pdf 
39
ter/STEM-ECR-v1.0/annotation-guidelines-for-scientific-linked-data.pdf 
            
40
\"Guidelines\").\r\n\r\n###Supporting Publication\r\nD'Souza, J., 
40
\"Guidelines\").\r\n\r\n###Supporting Publication\r\nD'Souza, J., 
            
41
Hoppe, A., Brack, A., Jaradeh, M., Auer, S., & Ewerth, R. (2020). [The 
41
Hoppe, A., Brack, A., Jaradeh, M., Auer, S., & Ewerth, R. (2020). [The 
            
42
STEM-ECR Dataset: Grounding Scientific Entity References in STEM 
42
STEM-ECR Dataset: Grounding Scientific Entity References in STEM 
            
43
Scholarly Content to Authoritative Encyclopedic and Lexicographic 
43
Scholarly Content to Authoritative Encyclopedic and Lexicographic 
            
44
Sources](https://www.aclweb.org/anthology/2020.lrec-1.268). In 
44
Sources](https://www.aclweb.org/anthology/2020.lrec-1.268). In 
            
45
Proceedings of The 12th Language Resources and Evaluation Conference 
45
Proceedings of The 12th Language Resources and Evaluation Conference 
            
46
(pp. 2192\u20132203). European Language Resources 
46
(pp. 2192\u20132203). European Language Resources 
            
47
Association.\r\n\r\n###Useful Links\r\n* 
47
Association.\r\n\r\n###Useful Links\r\n* 
            
48
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
48
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
            
49
https://brat.nlplab.org/\r\n* 
49
https://brat.nlplab.org/\r\n* 
            
50
https://dumps.wikimedia.org/enwiki/20190920/\r\n* 
50
https://dumps.wikimedia.org/enwiki/20190920/\r\n* 
            
51
https://dumps.wikimedia.org/enwiktionary/20190920/\r\n* 
51
https://dumps.wikimedia.org/enwiktionary/20190920/\r\n* 
            
52
https://dkpro.github.io/dkpro-jwpl/\r\n* 
52
https://dkpro.github.io/dkpro-jwpl/\r\n* 
            
53
https://dkpro.github.io/dkpro-jwktl/\r\n* https://orkg.org/orkg",
53
https://dkpro.github.io/dkpro-jwktl/\r\n* https://orkg.org/orkg",
            
n
54
  "num_resources": 3,
n
54
  "num_resources": 2,
            
55
  "num_tags": 7,
55
  "num_tags": 7,
            
56
  "organization": {
56
  "organization": {
            
57
    "approval_status": "approved",
57
    "approval_status": "approved",
            
58
    "created": "2017-11-23T17:30:37.757128",
58
    "created": "2017-11-23T17:30:37.757128",
            
59
    "description": "The German National Library of Science and 
59
    "description": "The German National Library of Science and 
            
60
Technology, abbreviated TIB, is the national library of the Federal 
60
Technology, abbreviated TIB, is the national library of the Federal 
            
61
Republic of Germany for all fields of engineering, technology, and the 
61
Republic of Germany for all fields of engineering, technology, and the 
            
62
natural sciences.",
62
natural sciences.",
            
63
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
63
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
64
    "image_url": 
64
    "image_url": 
            
65
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
65
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
66
    "is_organization": true,
66
    "is_organization": true,
            
67
    "name": "tib",
67
    "name": "tib",
            
68
    "state": "active",
68
    "state": "active",
            
69
    "title": "TIB",
69
    "title": "TIB",
            
70
    "type": "organization"
70
    "type": "organization"
            
71
  },
71
  },
            
72
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
72
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
73
  "private": false,
73
  "private": false,
            
74
  "relationships_as_object": [],
74
  "relationships_as_object": [],
            
75
  "relationships_as_subject": [],
75
  "relationships_as_subject": [],
            
76
  "repository_name": "Leibniz University Hannover",
76
  "repository_name": "Leibniz University Hannover",
            
77
  "resources": [
77
  "resources": [
            
78
    {
78
    {
            
79
      "cache_last_updated": null,
79
      "cache_last_updated": null,
            
80
      "cache_url": null,
80
      "cache_url": null,
            
81
      "created": "2020-02-13T13:08:18.655742",
81
      "created": "2020-02-13T13:08:18.655742",
            
n
82
      "datastore_active": false,
n

            
83
      "description": "",
82
      "description": "",
            
84
      "format": "ZIP",
83
      "format": "ZIP",
            
85
      "hash": "",
84
      "hash": "",
            
86
      "id": "fc7cccac-3b90-480f-9523-8ac727e18900",
85
      "id": "fc7cccac-3b90-480f-9523-8ac727e18900",
            
87
      "last_modified": "2020-02-13T13:21:44.613089",
86
      "last_modified": "2020-02-13T13:21:44.613089",
            
n
88
      "metadata_modified": "2021-10-14T10:16:07.249242",
n
87
      "metadata_modified": "2023-01-12T13:14:26.249764",
            
89
      "mimetype": "application/zip",
88
      "mimetype": "application/zip",
            
90
      "mimetype_inner": null,
89
      "mimetype_inner": null,
            
91
      "name": "Scientific Entity Annotations",
90
      "name": "Scientific Entity Annotations",
            
92
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
91
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
93
      "position": 0,
92
      "position": 0,
            
94
      "resource_type": null,
93
      "resource_type": null,
            
n
95
      "revision_id": "2c794064-aeb9-43fc-848e-078841cd40e3",
n

            
96
      "size": 10224852,
94
      "size": 10224852,
            
97
      "state": "active",
95
      "state": "active",
            
98
      "url": 
96
      "url": 
            
99
90-480f-9523-8ac727e18900/download/scientific_entity_annotations.zip",
97
90-480f-9523-8ac727e18900/download/scientific_entity_annotations.zip",
            
100
      "url_type": ""
98
      "url_type": ""
            
101
    },
99
    },
            
102
    {
100
    {
            
103
      "cache_last_updated": null,
101
      "cache_last_updated": null,
            
104
      "cache_url": null,
102
      "cache_url": null,
            
105
      "created": "2020-02-13T13:09:17.296000",
103
      "created": "2020-02-13T13:09:17.296000",
            
n
106
      "datastore_active": false,
n

            
107
      "description": "",
104
      "description": "",
            
108
      "format": "ZIP",
105
      "format": "ZIP",
            
109
      "hash": "",
106
      "hash": "",
            
110
      "id": "72362aa4-27d7-48c5-a2c5-c22674b61813",
107
      "id": "72362aa4-27d7-48c5-a2c5-c22674b61813",
            
111
      "last_modified": "2020-02-13T13:25:24.392378",
108
      "last_modified": "2020-02-13T13:25:24.392378",
            
n
112
      "metadata_modified": "2021-10-14T10:16:07.250459",
n
109
      "metadata_modified": "2023-01-12T13:14:26.249897",
            
113
      "mimetype": "application/zip",
110
      "mimetype": "application/zip",
            
114
      "mimetype_inner": null,
111
      "mimetype_inner": null,
            
115
      "name": "Entity Resolution Annotations",
112
      "name": "Entity Resolution Annotations",
            
116
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
113
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
117
      "position": 1,
114
      "position": 1,
            
118
      "resource_type": null,
115
      "resource_type": null,
            
n
119
      "revision_id": "6a64be41-292b-4d8b-a3f0-4fc9bb674c03",
n

            
120
      "size": 1469015,
116
      "size": 1469015,
            
121
      "state": "active",
117
      "state": "active",
            
122
      "url": 
118
      "url": 
            
123
d7-48c5-a2c5-c22674b61813/download/entity_resolution_annotations.zip",
119
d7-48c5-a2c5-c22674b61813/download/entity_resolution_annotations.zip",
            
124
      "url_type": ""
120
      "url_type": ""
            
n
125
    },
n

            
126
    {

            
127
      "cache_last_updated": null,

            
128
      "cache_url": null,

            
129
      "created": "2020-06-08T13:14:58.773192",

            
130
      "datastore_active": false,

            
131
      "description": "",

            
132
      "downloadall_datapackage_hash": 

            
133
"1b1ba633c014dc9504c10e8845172657",

            
134
      "downloadall_metadata_modified": "2020-02-13T14:32:22.433639",

            
135
      "format": "ZIP",

            
136
      "hash": "",

            
137
      "id": "0daa9116-6173-43ad-9bc4-e5724eb81efc",

            
138
      "last_modified": "2020-06-08T13:14:58.626684",

            
139
      "metadata_modified": "2021-10-14T10:16:07.251700",

            
140
      "mimetype": "application/zip",

            
141
      "mimetype_inner": null,

            
142
      "name": "All resource data",

            
143
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",

            
144
      "position": 2,

            
145
      "resource_type": null,

            
146
      "revision_id": "d2fd281c-0bcf-45b4-a501-922ce57290a0",

            
147
      "size": 11561551,

            
148
      "state": "active",

            
149
      "url": 

            
150
aa9116-6173-43ad-9bc4-e5724eb81efc/download/stem-ecr-v1-0-pad0zt.zip",

            
151
      "url_type": ""

            
152
    }
121
    }
            
153
  ],
122
  ],
            
154
  "source_metadata_created": "2020-02-13T12:57:09.939518",
123
  "source_metadata_created": "2020-02-13T12:57:09.939518",
            
t
155
  "source_metadata_modified": "2020-07-03T12:18:44.162642",
t
124
  "source_metadata_modified": "2022-01-20T11:00:07.087172",
            
156
  "state": "active",
125
  "state": "active",
            
157
  "tags": [
126
  "tags": [
            
158
    {
127
    {
            
159
      "display_name": "entity classification",
128
      "display_name": "entity classification",
            
160
      "id": "3e4235c4-6e2c-4915-aa12-60c2fedb9e43",
129
      "id": "3e4235c4-6e2c-4915-aa12-60c2fedb9e43",
            
161
      "name": "entity classification",
130
      "name": "entity classification",
            
162
      "state": "active",
131
      "state": "active",
            
163
      "vocabulary_id": null
132
      "vocabulary_id": null
            
164
    },
133
    },
            
165
    {
134
    {
            
166
      "display_name": "entity linking",
135
      "display_name": "entity linking",
            
167
      "id": "5ab0359d-b2b8-41b6-a4ed-84d6f26737fe",
136
      "id": "5ab0359d-b2b8-41b6-a4ed-84d6f26737fe",
            
168
      "name": "entity linking",
137
      "name": "entity linking",
            
169
      "state": "active",
138
      "state": "active",
            
170
      "vocabulary_id": null
139
      "vocabulary_id": null
            
171
    },
140
    },
            
172
    {
141
    {
            
173
      "display_name": "entity recognition",
142
      "display_name": "entity recognition",
            
174
      "id": "fc03c9dd-f1f5-46b5-85b7-6c0c696b66c6",
143
      "id": "fc03c9dd-f1f5-46b5-85b7-6c0c696b66c6",
            
175
      "name": "entity recognition",
144
      "name": "entity recognition",
            
176
      "state": "active",
145
      "state": "active",
            
177
      "vocabulary_id": null
146
      "vocabulary_id": null
            
178
    },
147
    },
            
179
    {
148
    {
            
180
      "display_name": "entity resolution",
149
      "display_name": "entity resolution",
            
181
      "id": "de6c1417-0f73-42a0-b1d8-cb461e039ecb",
150
      "id": "de6c1417-0f73-42a0-b1d8-cb461e039ecb",
            
182
      "name": "entity resolution",
151
      "name": "entity resolution",
            
183
      "state": "active",
152
      "state": "active",
            
184
      "vocabulary_id": null
153
      "vocabulary_id": null
            
185
    },
154
    },
            
186
    {
155
    {
            
187
      "display_name": "evaluation corpus",
156
      "display_name": "evaluation corpus",
            
188
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
157
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
            
189
      "name": "evaluation corpus",
158
      "name": "evaluation corpus",
            
190
      "state": "active",
159
      "state": "active",
            
191
      "vocabulary_id": null
160
      "vocabulary_id": null
            
192
    },
161
    },
            
193
    {
162
    {
            
194
      "display_name": "language resource",
163
      "display_name": "language resource",
            
195
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
164
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
            
196
      "name": "language resource",
165
      "name": "language resource",
            
197
      "state": "active",
166
      "state": "active",
            
198
      "vocabulary_id": null
167
      "vocabulary_id": null
            
199
    },
168
    },
            
200
    {
169
    {
            
201
      "display_name": "word sense disambiguation",
170
      "display_name": "word sense disambiguation",
            
202
      "id": "0f9b6e24-3a99-454f-afb9-ab4fb6f22e9d",
171
      "id": "0f9b6e24-3a99-454f-afb9-ab4fb6f22e9d",
            
203
      "name": "word sense disambiguation",
172
      "name": "word sense disambiguation",
            
204
      "state": "active",
173
      "state": "active",
            
205
      "vocabulary_id": null
174
      "vocabulary_id": null
            
206
    }
175
    }
            
207
  ],
176
  ],
            
208
  "terms_of_usage": "Yes",
177
  "terms_of_usage": "Yes",
            
209
  "title": "STEM-ECR-v1.0",
178
  "title": "STEM-ECR-v1.0",
            
210
  "type": "vdataset",
179
  "type": "vdataset",
            
211
  "url": "https://data.uni-hannover.de/dataset/stem-ecr-v1-0",
180
  "url": "https://data.uni-hannover.de/dataset/stem-ecr-v1-0",
            
212
  "version": "1.0"
181
  "version": "1.0"
            
213
}
182
}