Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "Jennifer D'Souza",
2
  "author": "Jennifer D'Souza",
            
3
  "author_email": "jennifer.dsouza@tib.eu",
3
  "author_email": "jennifer.dsouza@tib.eu",
            
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
5
  "doi": "10.25835/heyid7l7",
5
  "doi": "10.25835/heyid7l7",
            
6
  "doi_date_published": "2022-05-24",
6
  "doi_date_published": "2022-05-24",
            
7
  "doi_publisher": "LUIS",
7
  "doi_publisher": "LUIS",
            
8
  "doi_status": "true",
8
  "doi_status": "true",
            
9
  "domain": "https://data.uni-hannover.de",
9
  "domain": "https://data.uni-hannover.de",
            
10
  "groups": [],
10
  "groups": [],
            
11
  "have_copyright": "Yes",
11
  "have_copyright": "Yes",
            
12
  "id": "24dea2a0-39bf-4a15-bf41-ed46c530f679",
12
  "id": "24dea2a0-39bf-4a15-bf41-ed46c530f679",
            
13
  "isopen": false,
13
  "isopen": false,
            
14
  "license_id": "CC-BY-SA-3.0",
14
  "license_id": "CC-BY-SA-3.0",
            
15
  "license_title": "CC-BY-SA-3.0",
15
  "license_title": "CC-BY-SA-3.0",
            
16
  "maintainer": "Jennifer D'Souza",
16
  "maintainer": "Jennifer D'Souza",
            
17
  "maintainer_email": "jennifer.dsouza@tib.eu",
17
  "maintainer_email": "jennifer.dsouza@tib.eu",
            
18
  "metadata_created": "2023-01-12T13:14:26.388788",
18
  "metadata_created": "2023-01-12T13:14:26.388788",
            
n
19
  "metadata_modified": "2023-01-12T13:14:26.388794",
n
19
  "metadata_modified": "2023-08-04T08:46:48.461125",
            
20
  "name": "luh-stem-ner-60k",
20
  "name": "luh-stem-ner-60k",
            
21
  "notes": "##A Large-scale Dataset of STEM Science as PROCESS, 
21
  "notes": "##A Large-scale Dataset of STEM Science as PROCESS, 
            
22
METHOD, MATERIAL, and DATA Named Entities\r\n\r\n###This repository 
22
METHOD, MATERIAL, and DATA Named Entities\r\n\r\n###This repository 
            
23
hosts data as a follow-up study to the following 
23
hosts data as a follow-up study to the following 
            
24
publications\r\n\r\nD'Souza, J., Hoppe, A., Brack, A., Jaradeh, M., 
24
publications\r\n\r\nD'Souza, J., Hoppe, A., Brack, A., Jaradeh, M., 
            
25
Auer, S., & Ewerth, R. (2020). [The STEM-ECR Dataset: Grounding 
25
Auer, S., & Ewerth, R. (2020). [The STEM-ECR Dataset: Grounding 
            
26
Scientific Entity References in STEM Scholarly Content to 
26
Scientific Entity References in STEM Scholarly Content to 
            
27
Authoritative Encyclopedic and Lexicographic 
27
Authoritative Encyclopedic and Lexicographic 
            
28
Sources.](https://aclanthology.org/2020.lrec-1.268/) In Proceedings of 
28
Sources.](https://aclanthology.org/2020.lrec-1.268/) In Proceedings of 
            
29
The 12th Language Resources and Evaluation Conference (pp. 
29
The 12th Language Resources and Evaluation Conference (pp. 
            
30
2192\u20132203). European Language Resources 
30
2192\u20132203). European Language Resources 
            
31
Association.\r\n\r\nBrack, A., D\u2019Souza, J., Hoppe, A., Auer, S., 
31
Association.\r\n\r\nBrack, A., D\u2019Souza, J., Hoppe, A., Auer, S., 
            
32
Ewerth, R. (2020). [Domain-Independent Extraction of Scientific 
32
Ewerth, R. (2020). [Domain-Independent Extraction of Scientific 
            
33
Concepts from Research 
33
Concepts from Research 
            
34
Articles](https://doi.org/10.1007/978-3-030-45439-5_17). In: , et al. 
34
Articles](https://doi.org/10.1007/978-3-030-45439-5_17). In: , et al. 
            
35
Advances in Information Retrieval. ECIR 2020. Lecture Notes in 
35
Advances in Information Retrieval. ECIR 2020. Lecture Notes in 
            
36
Computer Science, vol 12035. Springer, Cham. 
36
Computer Science, vol 12035. Springer, Cham. 
            
37
https://doi.org/10.1007/978-3-030-45439-5_17\r\n\r\nSupporting dataset 
37
https://doi.org/10.1007/978-3-030-45439-5_17\r\n\r\nSupporting dataset 
            
38
link 
38
link 
            
39
annover.de/dataset/stem-ecr-v1-0)\r\n\r\n###Description\r\n\r\nRoughly 
39
annover.de/dataset/stem-ecr-v1-0)\r\n\r\n###Description\r\n\r\nRoughly 
            
40
60,000 titles and abstracts of scholarly articles with the CC-BY 
40
60,000 titles and abstracts of scholarly articles with the CC-BY 
            
41
redistributable license were downloaded from Elsevier. The articles 
41
redistributable license were downloaded from Elsevier. The articles 
            
42
spanned 10 STEM domains which were the most prolific on Elsevier viz., 
42
spanned 10 STEM domains which were the most prolific on Elsevier viz., 
            
43
*Agriculture*, *Astronomy*, *Biology*, *Chemistry*, *Computer 
43
*Agriculture*, *Astronomy*, *Biology*, *Chemistry*, *Computer 
            
44
Science*, *Earth Science*, *Engineering*, *Material Science*, and 
44
Science*, *Earth Science*, *Engineering*, *Material Science*, and 
            
45
*Mathematics*.\r\nThe STEM NER system reported in the publication 
45
*Mathematics*.\r\nThe STEM NER system reported in the publication 
            
46
above was applied on these articles. An automatically extracted 
46
above was applied on these articles. An automatically extracted 
            
47
dataset of 4 typed entities, viz., *Process*, *Method*, *Material*, 
47
dataset of 4 typed entities, viz., *Process*, *Method*, *Material*, 
            
48
and *Data* was created.\r\n\r\n### What this repository 
48
and *Data* was created.\r\n\r\n### What this repository 
            
49
contains?\r\n\r\nAggregated lists of *Process*, *Method*, *Material*, 
49
contains?\r\n\r\nAggregated lists of *Process*, *Method*, *Material*, 
            
50
and *Data* entities with respective occurrence counts extracted from 
50
and *Data* entities with respective occurrence counts extracted from 
            
51
59,984 scholarly publications organized per the 10 STEM domains 
51
59,984 scholarly publications organized per the 10 STEM domains 
            
52
considered.\r\n\r\nAdditionally, the list of Elsevier CC-BY articles 
52
considered.\r\n\r\nAdditionally, the list of Elsevier CC-BY articles 
            
53
used in this study are provided in the `raw-data` directory of the 
53
used in this study are provided in the `raw-data` directory of the 
            
54
repository.\r\n\r\n###Useful Links\r\n* 
54
repository.\r\n\r\n###Useful Links\r\n* 
            
55
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
55
https://github.com/elsevierlabs/OA-STM-Corpus/\r\n* 
            
56
https://orkg.org/orkg",
56
https://orkg.org/orkg",
            
57
  "num_resources": 1,
57
  "num_resources": 1,
            
58
  "num_tags": 7,
58
  "num_tags": 7,
            
59
  "organization": {
59
  "organization": {
            
60
    "approval_status": "approved",
60
    "approval_status": "approved",
            
61
    "created": "2017-11-23T17:30:37.757128",
61
    "created": "2017-11-23T17:30:37.757128",
            
62
    "description": "The German National Library of Science and 
62
    "description": "The German National Library of Science and 
            
63
Technology, abbreviated TIB, is the national library of the Federal 
63
Technology, abbreviated TIB, is the national library of the Federal 
            
64
Republic of Germany for all fields of engineering, technology, and the 
64
Republic of Germany for all fields of engineering, technology, and the 
            
65
natural sciences.",
65
natural sciences.",
            
66
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
66
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
67
    "image_url": 
67
    "image_url": 
            
68
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
68
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
69
    "is_organization": true,
69
    "is_organization": true,
            
70
    "name": "tib",
70
    "name": "tib",
            
71
    "state": "active",
71
    "state": "active",
            
72
    "title": "TIB",
72
    "title": "TIB",
            
73
    "type": "organization"
73
    "type": "organization"
            
74
  },
74
  },
            
75
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
75
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
76
  "private": false,
76
  "private": false,
            
77
  "relationships_as_object": [],
77
  "relationships_as_object": [],
            
78
  "relationships_as_subject": [],
78
  "relationships_as_subject": [],
            
79
  "repository_name": "Leibniz University Hannover",
79
  "repository_name": "Leibniz University Hannover",
            
80
  "resources": [
80
  "resources": [
            
81
    {
81
    {
            
82
      "cache_last_updated": null,
82
      "cache_last_updated": null,
            
83
      "cache_url": null,
83
      "cache_url": null,
            
84
      "created": "2022-05-24T07:49:55.940431",
84
      "created": "2022-05-24T07:49:55.940431",
            
85
      "description": "",
85
      "description": "",
            
86
      "format": "ZIP",
86
      "format": "ZIP",
            
87
      "hash": "",
87
      "hash": "",
            
88
      "id": "f34d0e46-2821-451f-b483-1ecd6fff51f9",
88
      "id": "f34d0e46-2821-451f-b483-1ecd6fff51f9",
            
89
      "last_modified": "2022-05-24T07:49:55.890558",
89
      "last_modified": "2022-05-24T07:49:55.890558",
            
n
90
      "metadata_modified": "2023-01-12T13:14:26.378059",
n
90
      "metadata_modified": "2023-08-04T08:46:48.464692",
            
91
      "mimetype": "application/zip",
91
      "mimetype": "application/zip",
            
92
      "mimetype_inner": null,
92
      "mimetype_inner": null,
            
93
      "name": "STEM-NER-60k",
93
      "name": "STEM-NER-60k",
            
94
      "package_id": "24dea2a0-39bf-4a15-bf41-ed46c530f679",
94
      "package_id": "24dea2a0-39bf-4a15-bf41-ed46c530f679",
            
95
      "position": 0,
95
      "position": 0,
            
96
      "resource_type": null,
96
      "resource_type": null,
            
97
      "size": 36715541,
97
      "size": 36715541,
            
98
      "state": "active",
98
      "state": "active",
            
99
      "url": 
99
      "url": 
            
100
ource/f34d0e46-2821-451f-b483-1ecd6fff51f9/download/stem-ner-60k.zip",
100
ource/f34d0e46-2821-451f-b483-1ecd6fff51f9/download/stem-ner-60k.zip",
            
101
      "url_type": ""
101
      "url_type": ""
            
102
    }
102
    }
            
103
  ],
103
  ],
            
t
t
104
  "services_used_list": "",
            
104
  "source_metadata_created": "2022-05-24T07:41:50.698890",
105
  "source_metadata_created": "2022-05-24T07:41:50.698890",
            
105
  "source_metadata_modified": "2022-05-24T13:26:08.956853",
106
  "source_metadata_modified": "2022-05-24T13:26:08.956853",
            
106
  "state": "active",
107
  "state": "active",
            
107
  "tags": [
108
  "tags": [
            
108
    {
109
    {
            
109
      "display_name": "NER",
110
      "display_name": "NER",
            
110
      "id": "265fae3c-9afa-48c1-8fa8-7ce5e6e1c122",
111
      "id": "265fae3c-9afa-48c1-8fa8-7ce5e6e1c122",
            
111
      "name": "NER",
112
      "name": "NER",
            
112
      "state": "active",
113
      "state": "active",
            
113
      "vocabulary_id": null
114
      "vocabulary_id": null
            
114
    },
115
    },
            
115
    {
116
    {
            
116
      "display_name": "evaluation corpus",
117
      "display_name": "evaluation corpus",
            
117
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
118
      "id": "e18bfbea-e418-4aca-acef-fa2087bc77b0",
            
118
      "name": "evaluation corpus",
119
      "name": "evaluation corpus",
            
119
      "state": "active",
120
      "state": "active",
            
120
      "vocabulary_id": null
121
      "vocabulary_id": null
            
121
    },
122
    },
            
122
    {
123
    {
            
123
      "display_name": "language resource",
124
      "display_name": "language resource",
            
124
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
125
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
            
125
      "name": "language resource",
126
      "name": "language resource",
            
126
      "state": "active",
127
      "state": "active",
            
127
      "vocabulary_id": null
128
      "vocabulary_id": null
            
128
    },
129
    },
            
129
    {
130
    {
            
130
      "display_name": "named entity recognition",
131
      "display_name": "named entity recognition",
            
131
      "id": "2c89c618-a7b7-4d1b-984b-aee05fb83b1e",
132
      "id": "2c89c618-a7b7-4d1b-984b-aee05fb83b1e",
            
132
      "name": "named entity recognition",
133
      "name": "named entity recognition",
            
133
      "state": "active",
134
      "state": "active",
            
134
      "vocabulary_id": null
135
      "vocabulary_id": null
            
135
    },
136
    },
            
136
    {
137
    {
            
137
      "display_name": "natural language processing",
138
      "display_name": "natural language processing",
            
138
      "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
139
      "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
            
139
      "name": "natural language processing",
140
      "name": "natural language processing",
            
140
      "state": "active",
141
      "state": "active",
            
141
      "vocabulary_id": null
142
      "vocabulary_id": null
            
142
    },
143
    },
            
143
    {
144
    {
            
144
      "display_name": "scholarly named entity recognition",
145
      "display_name": "scholarly named entity recognition",
            
145
      "id": "3d949403-5bb3-468b-a9c1-086b5fb1d79e",
146
      "id": "3d949403-5bb3-468b-a9c1-086b5fb1d79e",
            
146
      "name": "scholarly named entity recognition",
147
      "name": "scholarly named entity recognition",
            
147
      "state": "active",
148
      "state": "active",
            
148
      "vocabulary_id": null
149
      "vocabulary_id": null
            
149
    },
150
    },
            
150
    {
151
    {
            
151
      "display_name": "scientific named entity recognition",
152
      "display_name": "scientific named entity recognition",
            
152
      "id": "7e50bb81-b464-472c-aa9d-25236a2bede2",
153
      "id": "7e50bb81-b464-472c-aa9d-25236a2bede2",
            
153
      "name": "scientific named entity recognition",
154
      "name": "scientific named entity recognition",
            
154
      "state": "active",
155
      "state": "active",
            
155
      "vocabulary_id": null
156
      "vocabulary_id": null
            
156
    }
157
    }
            
157
  ],
158
  ],
            
158
  "terms_of_usage": "Yes",
159
  "terms_of_usage": "Yes",
            
159
  "title": "STEM-NER-60k",
160
  "title": "STEM-NER-60k",
            
160
  "type": "vdataset",
161
  "type": "vdataset",
            
161
  "url": "https://data.uni-hannover.de/dataset/stem-ner-60k",
162
  "url": "https://data.uni-hannover.de/dataset/stem-ner-60k",
            
162
  "version": ""
163
  "version": ""
            
163
}
164
}