Changes

              
    

          
          
        
        

            
f
1
{
f
1
{
            
2
  "author": "Jennifer D'Souza and S\u00f6ren Auer and Ted Pedersen",
2
  "author": "Jennifer D'Souza and S\u00f6ren Auer and Ted Pedersen",
            
3
  "author_email": "",
3
  "author_email": "",
            
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
4
  "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700",
            
5
  "extras": [],
5
  "extras": [],
            
6
  "groups": [],
6
  "groups": [],
            
7
  "id": "2b92e3fd-1ab8-45bb-995c-6102b5bd2f5f",
7
  "id": "2b92e3fd-1ab8-45bb-995c-6102b5bd2f5f",
            
8
  "isopen": true,
8
  "isopen": true,
            
9
  "license_id": "cc-by-sa",
9
  "license_id": "cc-by-sa",
            
10
  "license_title": "Creative Commons Attribution Share-Alike",
10
  "license_title": "Creative Commons Attribution Share-Alike",
            
11
  "license_url": "http://www.opendefinition.org/licenses/cc-by-sa",
11
  "license_url": "http://www.opendefinition.org/licenses/cc-by-sa",
            
12
  "maintainer": "Jennifer D'Souza",
12
  "maintainer": "Jennifer D'Souza",
            
13
  "maintainer_email": "jennifer.dsouza@tib.eu",
13
  "maintainer_email": "jennifer.dsouza@tib.eu",
            
14
  "metadata_created": "2021-07-23T07:28:39.166946",
14
  "metadata_created": "2021-07-23T07:28:39.166946",
            
n
15
  "metadata_modified": "2021-07-23T07:28:39.166958",
n
15
  "metadata_modified": "2021-07-23T07:30:09.835196",
            
16
  "name": "semeval-2021-task-11-shared-task-dataset",
16
  "name": "semeval-2021-task-11-shared-task-dataset",
            
17
  "notes": "NLPContributionGraph - Structuring Scholarly NLP 
17
  "notes": "NLPContributionGraph - Structuring Scholarly NLP 
            
18
Contributions in the Open Research Knowledge 
18
Contributions in the Open Research Knowledge 
            
19
Graph\r\n\r\nBackground\r\n\r\nNLPContributionGraph was introduced as 
19
Graph\r\n\r\nBackground\r\n\r\nNLPContributionGraph was introduced as 
            
20
Task 11 at SemEval 2021 for the first time. The task is defined on a 
20
Task 11 at SemEval 2021 for the first time. The task is defined on a 
            
21
dataset of Natural Language Processing (NLP) scholarly articles with 
21
dataset of Natural Language Processing (NLP) scholarly articles with 
            
22
their contributions structured to be integrable within Knowledge Graph 
22
their contributions structured to be integrable within Knowledge Graph 
            
23
infrastructures such as the Open Research Knowledge Graph. The 
23
infrastructures such as the Open Research Knowledge Graph. The 
            
24
structured contribution annotations are provided as (1) Contribution 
24
structured contribution annotations are provided as (1) Contribution 
            
25
sentences : a set of sentences about the contribution in the article; 
25
sentences : a set of sentences about the contribution in the article; 
            
26
(2) Scientific terms and relations: a set of scientific terms and 
26
(2) Scientific terms and relations: a set of scientific terms and 
            
27
relational cue phrases extracted from the contribution sentences; and 
27
relational cue phrases extracted from the contribution sentences; and 
            
28
(3) Triples: semantic statements that pair scientific terms with a 
28
(3) Triples: semantic statements that pair scientific terms with a 
            
29
relation, modeled toward subject-predicate-object RDF statements for 
29
relation, modeled toward subject-predicate-object RDF statements for 
            
30
KG building. The Triples are organized under three (mandatory) or more 
30
KG building. The Triples are organized under three (mandatory) or more 
            
31
of twelve total information units (viz., ResearchProblem, Approach, 
31
of twelve total information units (viz., ResearchProblem, Approach, 
            
32
Model, Code, Dataset, ExperimentalSetup, Hyperparameters, Baselines, 
32
Model, Code, Dataset, ExperimentalSetup, Hyperparameters, Baselines, 
            
33
Results, Tasks, Experiments, and AblationAnalysis).\r\n\r\nThe Shared 
33
Results, Tasks, Experiments, and AblationAnalysis).\r\n\r\nThe Shared 
            
34
Task\r\n\r\nAs a complete submission for the Shared Task, given NLP 
34
Task\r\n\r\nAs a complete submission for the Shared Task, given NLP 
            
35
scholarly articles in plaintext format, systems had to automatically 
35
scholarly articles in plaintext format, systems had to automatically 
            
36
extract the following information: contribution sentences; scientific 
36
extract the following information: contribution sentences; scientific 
            
37
term and predicate phrases from the sentences; and * 
37
term and predicate phrases from the sentences; and * 
            
38
(subject,predicate,object) triple statements toward KG building 
38
(subject,predicate,object) triple statements toward KG building 
            
39
organized under three or more of twelve total information units.\r\n",
39
organized under three or more of twelve total information units.\r\n",
            
n
40
  "num_resources": 0,
n
40
  "num_resources": 1,
            
41
  "num_tags": 7,
41
  "num_tags": 7,
            
42
  "organization": {
42
  "organization": {
            
43
    "approval_status": "approved",
43
    "approval_status": "approved",
            
44
    "created": "2017-11-23T17:30:37.757128",
44
    "created": "2017-11-23T17:30:37.757128",
            
45
    "description": "The German National Library of Science and 
45
    "description": "The German National Library of Science and 
            
46
Technology, abbreviated TIB, is the national library of the Federal 
46
Technology, abbreviated TIB, is the national library of the Federal 
            
47
Republic of Germany for all fields of engineering, technology, and the 
47
Republic of Germany for all fields of engineering, technology, and the 
            
48
natural sciences.",
48
natural sciences.",
            
49
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
49
    "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
50
    "image_url": 
50
    "image_url": 
            
51
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
51
3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png",
            
52
    "is_organization": true,
52
    "is_organization": true,
            
53
    "name": "tib-iasis",
53
    "name": "tib-iasis",
            
54
    "state": "active",
54
    "state": "active",
            
55
    "title": "TIB",
55
    "title": "TIB",
            
56
    "type": "organization"
56
    "type": "organization"
            
57
  },
57
  },
            
58
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
58
  "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d",
            
59
  "private": false,
59
  "private": false,
            
60
  "relationships_as_object": [],
60
  "relationships_as_object": [],
            
61
  "relationships_as_subject": [],
61
  "relationships_as_subject": [],
            
t
62
  "resources": [],
t
62
  "resources": [
            
63
    {
            
64
      "cache_last_updated": null,
            
65
      "cache_url": null,
            
66
      "created": "2021-07-23T07:30:09.849592",
            
67
      "datastore_active": false,
            
68
      "description": "\r\nTraining Data for the NLPContributionGraph 
            
69
Shared Task 11 at SemEval-2021\r\n\r\nThe repository is organized as 
            
70
follows:\r\n\r\nREADME.md                            
            
71
\r\n[task-name-folder]/                                # 
            
72
natural_language_inference, paraphrase_generation, question_answering, 
            
73
relation_extraction, topic_models\r\n    \u251c\u2500\u2500 
            
74
[article-counter-folder]/                  # ranges between 0 to 100 
            
75
since we annotated varying numbers of articles per task\r\n    \u2502   
            
76
\u251c\u2500\u2500 [articlename].pdf                      # scholarly 
            
77
article pdf\r\n    \u2502   \u251c\u2500\u2500 
            
78
[articlename]-Grobid-out.txt           # plaintext output from the 
            
79
[Grobid parser](https://github.com/kermitt2/grobid)\r\n    \u2502   
            
80
\u251c\u2500\u2500 [articlename]-Stanza-out.txt           # plaintext 
            
81
preprocessed output from 
            
82
[Stanza](https://github.com/stanfordnlp/stanza)\r\n    \u2502   
            
83
\u251c\u2500\u2500 sentences.txt                          # annotated 
            
84
Contribution sentences in the file\r\n    \u2502   \u251c\u2500\u2500 
            
85
entities.txt                           # annotated entities in the 
            
86
Contribution sentences\r\n    \u2502   \u2514\u2500\u2500 info-units/                            
            
87
# the folder containing information units in JSON format\r\n    \u2502   
            
88
\u2502   \u2514\u2500\u2500 research-problem.json              # 
            
89
`research problem` mandatory information unit in json format\r\n    
            
90
\u2502   \u2502   \u2514\u2500\u2500 model.json                         
            
91
# `model` information unit in json format; in some articles it is 
            
92
called `approach`\r\n    \u2502   \u2502   \u2514\u2500\u2500 ...                                
            
93
# there are 12 information units in all and each article may be 
            
94
annotated by 3 or 6\r\n    \u2502   \u2514\u2500\u2500 triples/                               
            
95
# the folder containing information unit triples one per line\r\n    
            
96
\u2502   \u2502   \u2514\u2500\u2500 research-problem.txt               
            
97
# `research problem` triples (one research problem statement per 
            
98
line)\r\n    \u2502   \u2502   \u2514\u2500\u2500 model.txt                          
            
99
# `model` triples (one statement per line)\r\n    \u2502   \u2502   
            
100
\u2514\u2500\u2500 ...                                # there are 12 
            
101
information units in all and each article may be annotated by 3 or 
            
102
6\r\n    \u2502   \u2514\u2500\u2500 ...                                    
            
103
# there are between 1 to 100 articles annotated for each task, so this 
            
104
repeats for the remaining annotated articles\r\n    \u2514\u2500\u2500 
            
105
...                                        # there are 24 tasks 
            
106
selected overall, so this repeats 23 more times\r\n\r\n",
            
107
      "format": "json, pdf, txt",
            
108
      "hash": "",
            
109
      "id": "c4c7da41-4bc7-4512-9cba-611c570cf97f",
            
110
      "last_modified": null,
            
111
      "metadata_modified": "2021-07-23T07:30:09.838000",
            
112
      "mimetype": null,
            
113
      "mimetype_inner": null,
            
114
      "name": "Training Dataset",
            
115
      "package_id": "2b92e3fd-1ab8-45bb-995c-6102b5bd2f5f",
            
116
      "position": 0,
            
117
      "resource_type": null,
            
118
      "size": null,
            
119
      "state": "active",
            
120
      "url": "https://github.com/ncg-task/training-data",
            
121
      "url_type": null
            
122
    }
            
123
  ],
            
63
  "state": "draft",
124
  "state": "draft",
            
64
  "tags": [
125
  "tags": [
            
65
    {
126
    {
            
66
      "display_name": "dataset",
127
      "display_name": "dataset",
            
67
      "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b",
128
      "id": "ce5ad030-ca3d-47e6-abd1-5c92a2806f1b",
            
68
      "name": "dataset",
129
      "name": "dataset",
            
69
      "state": "active",
130
      "state": "active",
            
70
      "vocabulary_id": null
131
      "vocabulary_id": null
            
71
    },
132
    },
            
72
    {
133
    {
            
73
      "display_name": "language resource",
134
      "display_name": "language resource",
            
74
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
135
      "id": "95e3d7f3-d046-428b-98c7-93653d23a183",
            
75
      "name": "language resource",
136
      "name": "language resource",
            
76
      "state": "active",
137
      "state": "active",
            
77
      "vocabulary_id": null
138
      "vocabulary_id": null
            
78
    },
139
    },
            
79
    {
140
    {
            
80
      "display_name": "natural language processing",
141
      "display_name": "natural language processing",
            
81
      "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
142
      "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c",
            
82
      "name": "natural language processing",
143
      "name": "natural language processing",
            
83
      "state": "active",
144
      "state": "active",
            
84
      "vocabulary_id": null
145
      "vocabulary_id": null
            
85
    },
146
    },
            
86
    {
147
    {
            
87
      "display_name": "open research knowledge graph",
148
      "display_name": "open research knowledge graph",
            
88
      "id": "c9fb26fb-f92f-4740-899e-290c1a384971",
149
      "id": "c9fb26fb-f92f-4740-899e-290c1a384971",
            
89
      "name": "open research knowledge graph",
150
      "name": "open research knowledge graph",
            
90
      "state": "active",
151
      "state": "active",
            
91
      "vocabulary_id": null
152
      "vocabulary_id": null
            
92
    },
153
    },
            
93
    {
154
    {
            
94
      "display_name": "scholarly knowledge graphs",
155
      "display_name": "scholarly knowledge graphs",
            
95
      "id": "759ea23d-8996-4917-b4b5-d020b86f7d1a",
156
      "id": "759ea23d-8996-4917-b4b5-d020b86f7d1a",
            
96
      "name": "scholarly knowledge graphs",
157
      "name": "scholarly knowledge graphs",
            
97
      "state": "active",
158
      "state": "active",
            
98
      "vocabulary_id": null
159
      "vocabulary_id": null
            
99
    },
160
    },
            
100
    {
161
    {
            
101
      "display_name": "semeval",
162
      "display_name": "semeval",
            
102
      "id": "44b579c2-0954-4335-8e31-92288b06eb7e",
163
      "id": "44b579c2-0954-4335-8e31-92288b06eb7e",
            
103
      "name": "semeval",
164
      "name": "semeval",
            
104
      "state": "active",
165
      "state": "active",
            
105
      "vocabulary_id": null
166
      "vocabulary_id": null
            
106
    },
167
    },
            
107
    {
168
    {
            
108
      "display_name": "shared task",
169
      "display_name": "shared task",
            
109
      "id": "ffd2394b-4c6d-4c18-9d24-66e7e851bd2f",
170
      "id": "ffd2394b-4c6d-4c18-9d24-66e7e851bd2f",
            
110
      "name": "shared task",
171
      "name": "shared task",
            
111
      "state": "active",
172
      "state": "active",
            
112
      "vocabulary_id": null
173
      "vocabulary_id": null
            
113
    }
174
    }
            
114
  ],
175
  ],
            
115
  "title": "SemEval-2021 Task 11 Shared Task Dataset",
176
  "title": "SemEval-2021 Task 11 Shared Task Dataset",
            
116
  "type": "dataset",
177
  "type": "dataset",
            
117
  "url": "https://github.com/ncg-task/",
178
  "url": "https://github.com/ncg-task/",
            
118
  "version": "1.0"
179
  "version": "1.0"
            
119
}
180
}