Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
n
2
  "author": "Jennifer D\u2019Souza; Anett Hoppe; Arthur Brack; Mohamad 
n
2
  "author": "Jennifer D\u2019Souza",
            
3
Yaser Jaradeh; Soren Auer; Ralph Ewerth",

            
4
  "author_email": "jennifer.dsouza@tib.eu",
3
  "author_email": "jennifer.dsouza@tib.eu",
            
5
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
6
  "doi": "10.25835/0017546",
5
  "doi": "10.25835/0017546",
            
7
  "doi_date_published": "2020-02-13",
6
  "doi_date_published": "2020-02-13",
            
8
  "doi_publisher": "LUIS",
7
  "doi_publisher": "LUIS",
            
9
  "doi_status": "true",
8
  "doi_status": "true",
            
10
  "domain": "https://data.uni-hannover.de",
9
  "domain": "https://data.uni-hannover.de",
            
n
n
10
  "extra_authors": [
            
11
    {
            
12
      "extra_author": " Anett Hoppe"
            
13
    },
            
14
    {
            
15
      "extra_author": " Arthur Brack"
            
16
    },
            
17
    {
            
18
      "extra_author": " Mohamad Yaser Jaradeh"
            
19
    },
            
20
    {
            
21
      "extra_author": " Soren Auer"
            
22
    },
            
23
    {
            
24
      "extra_author": " Ralph Ewerth"
            
25
    }
            
26
  ],
            
11
  "groups": [],
27
  "groups": [],
            
12
  "have_copyright": "Yes",
28
  "have_copyright": "Yes",
            
13
  "id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
29
  "id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
14
  "isopen": false,
30
  "isopen": false,
            
15
  "license_id": "CC-BY-SA-3.0",
31
  "license_id": "CC-BY-SA-3.0",
            
16
  "license_title": "CC-BY-SA-3.0",
32
  "license_title": "CC-BY-SA-3.0",
            
17
  "maintainer": "Jennifer D'Souza",
33
  "maintainer": "Jennifer D'Souza",
            
18
  "maintainer_email": "jennifer.dsouza@tib.eu",
34
  "maintainer_email": "jennifer.dsouza@tib.eu",
            
19
  "metadata_created": "2021-10-14T10:16:07.262891",
35
  "metadata_created": "2021-10-14T10:16:07.262891",
            
n
20
  "metadata_modified": "2023-01-12T13:14:26.246076",
n
36
  "metadata_modified": "2023-08-04T08:46:48.328452",
            
21
  "name": "luh-stem-ecr-v1-0",
37
  "name": "luh-stem-ecr-v1-0",
            
22
  "notes": "##Grounding Scientific Entity References in STEM Scholarly 
38
  "notes": "##Grounding Scientific Entity References in STEM Scholarly 
            
23
Content to Authoritative Encyclopedic and Lexicographic 
39
Content to Authoritative Encyclopedic and Lexicographic 
            
24
Sources\r\n\r\nThe STEM ECR v1.0 dataset has been developed to provide 
40
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, 
41
a benchmark for the evaluation of scientific entity extraction, 
            
26
classification, and resolution tasks in a domain-independent fashion. 
42
classification, and resolution tasks in a domain-independent fashion. 
            
27
It comprises annotations for scientific entities in scientific 
43
It comprises annotations for scientific entities in scientific 
            
28
Abstracts drawn from 10 disciplines in Science, Technology, 
44
Abstracts drawn from 10 disciplines in Science, Technology, 
            
29
Engineering, and Medicine. The annotated entities are further grounded 
45
Engineering, and Medicine. The annotated entities are further grounded 
            
30
to Wikipedia and Wiktionary, respectively.\r\n\r\n###What this 
46
to Wikipedia and Wiktionary, respectively.\r\n\r\n###What this 
            
31
repository contains?\r\nThe dataset is organized in the following 
47
repository contains?\r\nThe dataset is organized in the following 
            
32
folders:\r\n\r\n* Scientific Entity Annotations: Contains annotations 
48
folders:\r\n\r\n* Scientific Entity Annotations: Contains annotations 
            
33
for Process, Material, Method, and Data scientific entities in the 
49
for Process, Material, Method, and Data scientific entities in the 
            
34
STEM dataset.\r\n* Scientific Entity Resolution: Annotations for the 
50
STEM dataset.\r\n* Scientific Entity Resolution: Annotations for the 
            
35
STEM dataset scientific entities with Entity Linking (EL) annotations 
51
STEM dataset scientific entities with Entity Linking (EL) annotations 
            
36
to Wikipedia and Word Sense Disambiguation (WSD) annotations to 
52
to Wikipedia and Word Sense Disambiguation (WSD) annotations to 
            
37
Wiktionary.\r\n\r\n\r\n###Annotation Guidelines\r\n\r\nThe annotation 
53
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 
54
guidelines that supported the creation of this corpus can be found 
            
39
ter/STEM-ECR-v1.0/annotation-guidelines-for-scientific-linked-data.pdf 
55
ter/STEM-ECR-v1.0/annotation-guidelines-for-scientific-linked-data.pdf 
            
40
\"Guidelines\").\r\n\r\n###Supporting Publication\r\nD'Souza, J., 
56
\"Guidelines\").\r\n\r\n###Supporting Publication\r\nD'Souza, J., 
            
41
Hoppe, A., Brack, A., Jaradeh, M., Auer, S., & Ewerth, R. (2020). [The 
57
Hoppe, A., Brack, A., Jaradeh, M., Auer, S., & Ewerth, R. (2020). [The 
            
42
STEM-ECR Dataset: Grounding Scientific Entity References in STEM 
58
STEM-ECR Dataset: Grounding Scientific Entity References in STEM 
            
43
Scholarly Content to Authoritative Encyclopedic and Lexicographic 
59
Scholarly Content to Authoritative Encyclopedic and Lexicographic 
            
44
Sources](https://www.aclweb.org/anthology/2020.lrec-1.268). In 
60
Sources](https://www.aclweb.org/anthology/2020.lrec-1.268). In 
            
45
Proceedings of The 12th Language Resources and Evaluation Conference 
61
Proceedings of The 12th Language Resources and Evaluation Conference 
            
46
(pp. 2192\u20132203). European Language Resources 
62
(pp. 2192\u20132203). European Language Resources 
            
47
Association.\r\n\r\n###Useful Links\r\n* 
63
Association.\r\n\r\n###Useful Links\r\n* 
            
48
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
64
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
            
49
https://brat.nlplab.org/\r\n* 
65
https://brat.nlplab.org/\r\n* 
            
50
https://dumps.wikimedia.org/enwiki/20190920/\r\n* 
66
https://dumps.wikimedia.org/enwiki/20190920/\r\n* 
            
51
https://dumps.wikimedia.org/enwiktionary/20190920/\r\n* 
67
https://dumps.wikimedia.org/enwiktionary/20190920/\r\n* 
            
52
https://dkpro.github.io/dkpro-jwpl/\r\n* 
68
https://dkpro.github.io/dkpro-jwpl/\r\n* 
            
53
https://dkpro.github.io/dkpro-jwktl/\r\n* https://orkg.org/orkg",
69
https://dkpro.github.io/dkpro-jwktl/\r\n* https://orkg.org/orkg",
            
54
  "num_resources": 2,
70
  "num_resources": 2,
            
55
  "num_tags": 7,
71
  "num_tags": 7,
            
56
  "organization": {
72
  "organization": {
            
57
    "approval_status": "approved",
73
    "approval_status": "approved",
            
58
    "created": "2017-11-23T17:30:37.757128",
74
    "created": "2017-11-23T17:30:37.757128",
            
59
    "description": "The German National Library of Science and 
75
    "description": "The German National Library of Science and 
            
60
Technology, abbreviated TIB, is the national library of the Federal 
76
Technology, abbreviated TIB, is the national library of the Federal 
            
61
Republic of Germany for all fields of engineering, technology, and the 
77
Republic of Germany for all fields of engineering, technology, and the 
            
62
natural sciences.",
78
natural sciences.",
            
63
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
79
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
64
    "image_url": 
80
    "image_url": 
            
65
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
81
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
66
    "is_organization": true,
82
    "is_organization": true,
            
67
    "name": "tib",
83
    "name": "tib",
            
68
    "state": "active",
84
    "state": "active",
            
69
    "title": "TIB",
85
    "title": "TIB",
            
70
    "type": "organization"
86
    "type": "organization"
            
71
  },
87
  },
            
72
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
88
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
73
  "private": false,
89
  "private": false,
            
74
  "relationships_as_object": [],
90
  "relationships_as_object": [],
            
75
  "relationships_as_subject": [],
91
  "relationships_as_subject": [],
            
76
  "repository_name": "Leibniz University Hannover",
92
  "repository_name": "Leibniz University Hannover",
            
77
  "resources": [
93
  "resources": [
            
78
    {
94
    {
            
79
      "cache_last_updated": null,
95
      "cache_last_updated": null,
            
80
      "cache_url": null,
96
      "cache_url": null,
            
81
      "created": "2020-02-13T13:08:18.655742",
97
      "created": "2020-02-13T13:08:18.655742",
            
82
      "description": "",
98
      "description": "",
            
83
      "format": "ZIP",
99
      "format": "ZIP",
            
84
      "hash": "",
100
      "hash": "",
            
85
      "id": "fc7cccac-3b90-480f-9523-8ac727e18900",
101
      "id": "fc7cccac-3b90-480f-9523-8ac727e18900",
            
86
      "last_modified": "2020-02-13T13:21:44.613089",
102
      "last_modified": "2020-02-13T13:21:44.613089",
            
n
87
      "metadata_modified": "2023-01-12T13:14:26.249764",
n
103
      "metadata_modified": "2023-08-04T08:46:48.332421",
            
88
      "mimetype": "application/zip",
104
      "mimetype": "application/zip",
            
89
      "mimetype_inner": null,
105
      "mimetype_inner": null,
            
90
      "name": "Scientific Entity Annotations",
106
      "name": "Scientific Entity Annotations",
            
91
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
107
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
92
      "position": 0,
108
      "position": 0,
            
93
      "resource_type": null,
109
      "resource_type": null,
            
94
      "size": 10224852,
110
      "size": 10224852,
            
95
      "state": "active",
111
      "state": "active",
            
96
      "url": 
112
      "url": 
            
97
90-480f-9523-8ac727e18900/download/scientific_entity_annotations.zip",
113
90-480f-9523-8ac727e18900/download/scientific_entity_annotations.zip",
            
98
      "url_type": ""
114
      "url_type": ""
            
99
    },
115
    },
            
100
    {
116
    {
            
101
      "cache_last_updated": null,
117
      "cache_last_updated": null,
            
102
      "cache_url": null,
118
      "cache_url": null,
            
103
      "created": "2020-02-13T13:09:17.296000",
119
      "created": "2020-02-13T13:09:17.296000",
            
104
      "description": "",
120
      "description": "",
            
105
      "format": "ZIP",
121
      "format": "ZIP",
            
106
      "hash": "",
122
      "hash": "",
            
107
      "id": "72362aa4-27d7-48c5-a2c5-c22674b61813",
123
      "id": "72362aa4-27d7-48c5-a2c5-c22674b61813",
            
108
      "last_modified": "2020-02-13T13:25:24.392378",
124
      "last_modified": "2020-02-13T13:25:24.392378",
            
n
109
      "metadata_modified": "2023-01-12T13:14:26.249897",
n
125
      "metadata_modified": "2023-08-04T08:46:48.332554",
            
110
      "mimetype": "application/zip",
126
      "mimetype": "application/zip",
            
111
      "mimetype_inner": null,
127
      "mimetype_inner": null,
            
112
      "name": "Entity Resolution Annotations",
128
      "name": "Entity Resolution Annotations",
            
113
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
129
      "package_id": "0a4d8d4e-f881-48f5-82e8-20c2c635e8bd",
            
114
      "position": 1,
130
      "position": 1,
            
115
      "resource_type": null,
131
      "resource_type": null,
            
116
      "size": 1469015,
132
      "size": 1469015,
            
117
      "state": "active",
133
      "state": "active",
            
118
      "url": 
134
      "url": 
            
119
d7-48c5-a2c5-c22674b61813/download/entity_resolution_annotations.zip",
135
d7-48c5-a2c5-c22674b61813/download/entity_resolution_annotations.zip",
            
120
      "url_type": ""
136
      "url_type": ""
            
121
    }
137
    }
            
122
  ],
138
  ],
            
t
t
139
  "services_used_list": "",
            
123
  "source_metadata_created": "2020-02-13T12:57:09.939518",
140
  "source_metadata_created": "2020-02-13T12:57:09.939518",
            
124
  "source_metadata_modified": "2022-01-20T11:00:07.087172",
141
  "source_metadata_modified": "2022-01-20T11:00:07.087172",
            
125
  "state": "active",
142
  "state": "active",
            
126
  "tags": [
143
  "tags": [
            
127
    {
144
    {
            
128
      "display_name": "entity classification",
145
      "display_name": "entity classification",
            
129
      "id": "3e4235c4-6e2c-4915-aa12-60c2fedb9e43",
146
      "id": "3e4235c4-6e2c-4915-aa12-60c2fedb9e43",
            
130
      "name": "entity classification",
147
      "name": "entity classification",
            
131
      "state": "active",
148
      "state": "active",
            
132
      "vocabulary_id": null
149
      "vocabulary_id": null
            
133
    },
150
    },
            
134
    {
151
    {
            
135
      "display_name": "entity linking",
152
      "display_name": "entity linking",
            
136
      "id": "5ab0359d-b2b8-41b6-a4ed-84d6f26737fe",
153
      "id": "5ab0359d-b2b8-41b6-a4ed-84d6f26737fe",
            
137
      "name": "entity linking",
154
      "name": "entity linking",
            
138
      "state": "active",
155
      "state": "active",
            
139
      "vocabulary_id": null
156
      "vocabulary_id": null
            
140
    },
157
    },
            
141
    {
158
    {
            
142
      "display_name": "entity recognition",
159
      "display_name": "entity recognition",
            
143
      "id": "fc03c9dd-f1f5-46b5-85b7-6c0c696b66c6",
160
      "id": "fc03c9dd-f1f5-46b5-85b7-6c0c696b66c6",
            
144
      "name": "entity recognition",
161
      "name": "entity recognition",
            
145
      "state": "active",
162
      "state": "active",
            
146
      "vocabulary_id": null
163
      "vocabulary_id": null
            
147
    },
164
    },
            
148
    {
165
    {
            
149
      "display_name": "entity resolution",
166
      "display_name": "entity resolution",
            
150
      "id": "de6c1417-0f73-42a0-b1d8-cb461e039ecb",
167
      "id": "de6c1417-0f73-42a0-b1d8-cb461e039ecb",
            
151
      "name": "entity resolution",
168
      "name": "entity resolution",
            
152
      "state": "active",
169
      "state": "active",
            
153
      "vocabulary_id": null
170
      "vocabulary_id": null
            
154
    },
171
    },
            
155
    {
172
    {
            
156
      "display_name": "evaluation corpus",
173
      "display_name": "evaluation corpus",
            
157
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
174
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
            
158
      "name": "evaluation corpus",
175
      "name": "evaluation corpus",
            
159
      "state": "active",
176
      "state": "active",
            
160
      "vocabulary_id": null
177
      "vocabulary_id": null
            
161
    },
178
    },
            
162
    {
179
    {
            
163
      "display_name": "language resource",
180
      "display_name": "language resource",
            
164
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
181
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
            
165
      "name": "language resource",
182
      "name": "language resource",
            
166
      "state": "active",
183
      "state": "active",
            
167
      "vocabulary_id": null
184
      "vocabulary_id": null
            
168
    },
185
    },
            
169
    {
186
    {
            
170
      "display_name": "word sense disambiguation",
187
      "display_name": "word sense disambiguation",
            
171
      "id": "0f9b6e24-3a99-454f-afb9-ab4fb6f22e9d",
188
      "id": "0f9b6e24-3a99-454f-afb9-ab4fb6f22e9d",
            
172
      "name": "word sense disambiguation",
189
      "name": "word sense disambiguation",
            
173
      "state": "active",
190
      "state": "active",
            
174
      "vocabulary_id": null
191
      "vocabulary_id": null
            
175
    }
192
    }
            
176
  ],
193
  ],
            
177
  "terms_of_usage": "Yes",
194
  "terms_of_usage": "Yes",
            
178
  "title": "STEM-ECR-v1.0",
195
  "title": "STEM-ECR-v1.0",
            
179
  "type": "vdataset",
196
  "type": "vdataset",
            
180
  "url": "https://data.uni-hannover.de/dataset/stem-ecr-v1-0",
197
  "url": "https://data.uni-hannover.de/dataset/stem-ecr-v1-0",
            
181
  "version": "1.0"
198
  "version": "1.0"
            
182
}
199
}