Changes
On August 4, 2023 at 8:46:41 AM UTC, admin:
-
Set author of NLPContributionGraph Trial Dataset to Jennifer D’Souza (previously Jennifer D’Souza, Soeren Auer)
f | 1 | { | f | 1 | { |
n | 2 | "author": "Jennifer D\u2019Souza, Soeren Auer", | n | 2 | "author": "Jennifer D\u2019Souza", |
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": "10.25835/0019761", | 5 | "doi": "10.25835/0019761", | ||
6 | "doi_date_published": "2020-07-03", | 6 | "doi_date_published": "2020-07-03", | ||
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", | ||
n | n | 10 | "extra_authors": [ | ||
11 | { | ||||
12 | "extra_author": " Soeren Auer" | ||||
13 | } | ||||
14 | ], | ||||
10 | "groups": [], | 15 | "groups": [], | ||
11 | "have_copyright": "Yes", | 16 | "have_copyright": "Yes", | ||
12 | "id": "3c23ef7a-45e8-47a0-b635-ce39006d2ba7", | 17 | "id": "3c23ef7a-45e8-47a0-b635-ce39006d2ba7", | ||
13 | "isopen": false, | 18 | "isopen": false, | ||
14 | "license_id": "CC-BY-SA-3.0", | 19 | "license_id": "CC-BY-SA-3.0", | ||
15 | "license_title": "CC-BY-SA-3.0", | 20 | "license_title": "CC-BY-SA-3.0", | ||
16 | "maintainer": "Jennifer D'Souza", | 21 | "maintainer": "Jennifer D'Souza", | ||
17 | "maintainer_email": "jennifer.dsouza@tib.eu", | 22 | "maintainer_email": "jennifer.dsouza@tib.eu", | ||
18 | "metadata_created": "2021-10-14T10:16:03.354056", | 23 | "metadata_created": "2021-10-14T10:16:03.354056", | ||
n | 19 | "metadata_modified": "2023-01-12T13:14:21.766915", | n | 24 | "metadata_modified": "2023-08-04T08:46:41.227172", |
20 | "name": "luh-nlpcontributions-pilot-dataset", | 25 | "name": "luh-nlpcontributions-pilot-dataset", | ||
21 | "notes": "##An Annotation Scheme for Machine Reading of Scholarly | 26 | "notes": "##An Annotation Scheme for Machine Reading of Scholarly | ||
22 | Contributions in Natural Language Processing Literature\r\n\r\nThis | 27 | Contributions in Natural Language Processing Literature\r\n\r\nThis | ||
23 | dataset is the result of a pilot annotation exercise to capture the | 28 | dataset is the result of a pilot annotation exercise to capture the | ||
24 | scholarly contributions in natural language processing (NLP) articles, | 29 | scholarly contributions in natural language processing (NLP) articles, | ||
25 | particularly, for the articles that discuss machine learning (ML) | 30 | particularly, for the articles that discuss machine learning (ML) | ||
26 | approaches for various information extraction tasks. The pilot | 31 | approaches for various information extraction tasks. The pilot | ||
27 | annotation exercise was performed on 50 NLP-ML scholarly articles | 32 | annotation exercise was performed on 50 NLP-ML scholarly articles | ||
28 | presenting contributions to the five information extraction tasks 1. | 33 | presenting contributions to the five information extraction tasks 1. | ||
29 | machine translation, 2. named entity recognition, 3. question | 34 | machine translation, 2. named entity recognition, 3. question | ||
30 | answering, 4. relation classification, and 5. text classification. | 35 | answering, 4. relation classification, and 5. text classification. | ||
31 | \r\n\r\nThe outcome of this pilot annotation exercise was two-fold: 1) | 36 | \r\n\r\nThe outcome of this pilot annotation exercise was two-fold: 1) | ||
32 | a preliminary annotation methodology, and 2) the dataset released in | 37 | a preliminary annotation methodology, and 2) the dataset released in | ||
33 | this repository.\r\n\r\nThe resulting annotation scheme is called | 38 | this repository.\r\n\r\nThe resulting annotation scheme is called | ||
34 | <b><i>NLPContributions</i></b>.\r\n\r\n###Supporting | 39 | <b><i>NLPContributions</i></b>.\r\n\r\n###Supporting | ||
35 | Publications\r\nD\u2019Souza, J., & Auer, S. (2020). NLPContributions: | 40 | Publications\r\nD\u2019Souza, J., & Auer, S. (2020). NLPContributions: | ||
36 | An Annotation Scheme for Machine Reading of Scholarly Contributions in | 41 | An Annotation Scheme for Machine Reading of Scholarly Contributions in | ||
37 | Natural Language Processing Literature. In C. Zhang, P. Mayr, W. Lu, & | 42 | Natural Language Processing Literature. In C. Zhang, P. Mayr, W. Lu, & | ||
38 | Y. Zhang (Eds.), Proceedings of the 1st Workshop on Extraction and | 43 | Y. Zhang (Eds.), Proceedings of the 1st Workshop on Extraction and | ||
39 | Evaluation of Knowledge Entities from Scientific Documents co-located | 44 | Evaluation of Knowledge Entities from Scientific Documents co-located | ||
40 | with the ACM/IEEE Joint Conference on Digital Libraries in 2020, | 45 | with the ACM/IEEE Joint Conference on Digital Libraries in 2020, | ||
41 | EEKE@JCDL 2020, Virtual Event, China, August 1st, 2020 (Vol. 2658, pp. | 46 | EEKE@JCDL 2020, Virtual Event, China, August 1st, 2020 (Vol. 2658, pp. | ||
42 | 16\u201327). \r\n\r\nD'Souza, Jennifer, and S\u00f6ren Auer. | 47 | 16\u201327). \r\n\r\nD'Souza, Jennifer, and S\u00f6ren Auer. | ||
43 | \"Sentence, Phrase, and Triple Annotations to Build a Knowledge Graph | 48 | \"Sentence, Phrase, and Triple Annotations to Build a Knowledge Graph | ||
44 | of Natural Language Processing Contributions\u2014A Trial Dataset.\" | 49 | of Natural Language Processing Contributions\u2014A Trial Dataset.\" | ||
45 | Journal of Data and Information Science, vol.6, no.3, 2021, pp.6-34. | 50 | Journal of Data and Information Science, vol.6, no.3, 2021, pp.6-34. | ||
46 | DOI: 10.2478/jdis-2021-0023 ", | 51 | DOI: 10.2478/jdis-2021-0023 ", | ||
47 | "num_resources": 1, | 52 | "num_resources": 1, | ||
48 | "num_tags": 8, | 53 | "num_tags": 8, | ||
49 | "organization": { | 54 | "organization": { | ||
50 | "approval_status": "approved", | 55 | "approval_status": "approved", | ||
51 | "created": "2017-11-23T17:30:37.757128", | 56 | "created": "2017-11-23T17:30:37.757128", | ||
52 | "description": "The German National Library of Science and | 57 | "description": "The German National Library of Science and | ||
53 | Technology, abbreviated TIB, is the national library of the Federal | 58 | Technology, abbreviated TIB, is the national library of the Federal | ||
54 | Republic of Germany for all fields of engineering, technology, and the | 59 | Republic of Germany for all fields of engineering, technology, and the | ||
55 | natural sciences.", | 60 | natural sciences.", | ||
56 | "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d", | 61 | "id": "0c5362f5-b99e-41db-8256-3d0d7549bf4d", | ||
57 | "image_url": | 62 | "image_url": | ||
58 | 3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png", | 63 | 3conf/ext/tib_tmpl_bootstrap/Resources/Public/images/TIB_Logo_en.png", | ||
59 | "is_organization": true, | 64 | "is_organization": true, | ||
60 | "name": "tib", | 65 | "name": "tib", | ||
61 | "state": "active", | 66 | "state": "active", | ||
62 | "title": "TIB", | 67 | "title": "TIB", | ||
63 | "type": "organization" | 68 | "type": "organization" | ||
64 | }, | 69 | }, | ||
65 | "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d", | 70 | "owner_org": "0c5362f5-b99e-41db-8256-3d0d7549bf4d", | ||
66 | "private": false, | 71 | "private": false, | ||
67 | "relationships_as_object": [], | 72 | "relationships_as_object": [], | ||
68 | "relationships_as_subject": [], | 73 | "relationships_as_subject": [], | ||
69 | "repository_name": "Leibniz University Hannover", | 74 | "repository_name": "Leibniz University Hannover", | ||
70 | "resources": [ | 75 | "resources": [ | ||
71 | { | 76 | { | ||
72 | "cache_last_updated": null, | 77 | "cache_last_updated": null, | ||
73 | "cache_url": null, | 78 | "cache_url": null, | ||
74 | "created": "2020-07-03T12:32:07.815445", | 79 | "created": "2020-07-03T12:32:07.815445", | ||
75 | "description": "Research contributions in NLP annotated as | 80 | "description": "Research contributions in NLP annotated as | ||
76 | structured data using the NLPContributionGraph scheme for structuring | 81 | structured data using the NLPContributionGraph scheme for structuring | ||
77 | scholarly contributions in the | 82 | scholarly contributions in the | ||
78 | [ORKG](https://www.orkg.org/orkg/).\r\n\r\nThe repository is organized | 83 | [ORKG](https://www.orkg.org/orkg/).\r\n\r\nThe repository is organized | ||
79 | as follows:\r\n\r\n [task-name-folder]/ | 84 | as follows:\r\n\r\n [task-name-folder]/ | ||
80 | # machine-translation, named-entity-recognition, question-answering, | 85 | # machine-translation, named-entity-recognition, question-answering, | ||
81 | relation-classification, text-classification\r\n | 86 | relation-classification, text-classification\r\n | ||
82 | \u251c\u2500\u2500 [article-counter-folder]/ # ranges | 87 | \u251c\u2500\u2500 [article-counter-folder]/ # ranges | ||
83 | from 0 to 9 since we annotated 10 articles per task\r\n \u2502 | 88 | from 0 to 9 since we annotated 10 articles per task\r\n \u2502 | ||
84 | \u2514\u2500\u2500 research-problem.json # `research | 89 | \u2514\u2500\u2500 research-problem.json # `research | ||
85 | problem` mandatory information unit in json format\r\n \u2502 | 90 | problem` mandatory information unit in json format\r\n \u2502 | ||
86 | \u2514\u2500\u2500 model.json # `model` | 91 | \u2514\u2500\u2500 model.json # `model` | ||
87 | information unit in json format; in some articles it is called | 92 | information unit in json format; in some articles it is called | ||
88 | `approach`\r\n \u2502 \u2514\u2500\u2500 ... | 93 | `approach`\r\n \u2502 \u2514\u2500\u2500 ... | ||
89 | # there are 8 main information units in all and each article may be | 94 | # there are 8 main information units in all and each article may be | ||
90 | annotated by 3 or 6\r\n \u2502 \u2514\u2500\u2500 triples/ | 95 | annotated by 3 or 6\r\n \u2502 \u2514\u2500\u2500 triples/ | ||
91 | # the folder containing information unit triples one per line\r\n | 96 | # the folder containing information unit triples one per line\r\n | ||
92 | \u2502 \u2502 \u2514\u2500\u2500 research-problem.txt | 97 | \u2502 \u2502 \u2514\u2500\u2500 research-problem.txt | ||
93 | # `research problem` triples (one research problem statement per | 98 | # `research problem` triples (one research problem statement per | ||
94 | line)\r\n \u2502 \u2502 \u2514\u2500\u2500 model.txt | 99 | line)\r\n \u2502 \u2502 \u2514\u2500\u2500 model.txt | ||
95 | # `model` triples (one statement per line)\r\n \u2502 \u2502 | 100 | # `model` triples (one statement per line)\r\n \u2502 \u2502 | ||
96 | \u2514\u2500\u2500 ... # there are 8 | 101 | \u2514\u2500\u2500 ... # there are 8 | ||
97 | main information units in all and each article may be annotated by 3 | 102 | main information units in all and each article may be annotated by 3 | ||
98 | or 6\r\n \u2502 \u2514\u2500\u2500 ... | 103 | or 6\r\n \u2502 \u2514\u2500\u2500 ... | ||
99 | # there are ten articles annotated for each task, so this repeats nine | 104 | # there are ten articles annotated for each task, so this repeats nine | ||
100 | more times\r\n \u2514\u2500\u2500 ... | 105 | more times\r\n \u2514\u2500\u2500 ... | ||
101 | # there are five tasks selected overall, so this repeats four more | 106 | # there are five tasks selected overall, so this repeats four more | ||
102 | times", | 107 | times", | ||
103 | "format": "JSON", | 108 | "format": "JSON", | ||
104 | "hash": "", | 109 | "hash": "", | ||
105 | "id": "29c065cf-7087-49e0-89aa-4901f90a528c", | 110 | "id": "29c065cf-7087-49e0-89aa-4901f90a528c", | ||
106 | "last_modified": "2020-07-24T12:03:36.054419", | 111 | "last_modified": "2020-07-24T12:03:36.054419", | ||
n | 107 | "metadata_modified": "2023-01-12T13:14:21.770546", | n | 112 | "metadata_modified": "2023-08-04T08:46:41.230513", |
108 | "mimetype": "application/zip", | 113 | "mimetype": "application/zip", | ||
109 | "mimetype_inner": null, | 114 | "mimetype_inner": null, | ||
110 | "name": "Trial data from the NLPContributionGraph scheme", | 115 | "name": "Trial data from the NLPContributionGraph scheme", | ||
111 | "package_id": "3c23ef7a-45e8-47a0-b635-ce39006d2ba7", | 116 | "package_id": "3c23ef7a-45e8-47a0-b635-ce39006d2ba7", | ||
112 | "position": 0, | 117 | "position": 0, | ||
113 | "resource_type": null, | 118 | "resource_type": null, | ||
114 | "size": 29426833, | 119 | "size": 29426833, | ||
115 | "state": "active", | 120 | "state": "active", | ||
116 | "url": "https://github.com/ncg-task/trial-data", | 121 | "url": "https://github.com/ncg-task/trial-data", | ||
117 | "url_type": "" | 122 | "url_type": "" | ||
118 | } | 123 | } | ||
119 | ], | 124 | ], | ||
t | t | 125 | "services_used_list": "", | ||
120 | "source_metadata_created": "2020-07-03T12:08:02.648914", | 126 | "source_metadata_created": "2020-07-03T12:08:02.648914", | ||
121 | "source_metadata_modified": "2022-02-21T13:09:17.617156", | 127 | "source_metadata_modified": "2022-02-21T13:09:17.617156", | ||
122 | "state": "active", | 128 | "state": "active", | ||
123 | "tags": [ | 129 | "tags": [ | ||
124 | { | 130 | { | ||
125 | "display_name": "corpus", | 131 | "display_name": "corpus", | ||
126 | "id": "95b6b4a3-2816-47b4-a9da-50ab21116c20", | 132 | "id": "95b6b4a3-2816-47b4-a9da-50ab21116c20", | ||
127 | "name": "corpus", | 133 | "name": "corpus", | ||
128 | "state": "active", | 134 | "state": "active", | ||
129 | "vocabulary_id": null | 135 | "vocabulary_id": null | ||
130 | }, | 136 | }, | ||
131 | { | 137 | { | ||
132 | "display_name": "machine reading", | 138 | "display_name": "machine reading", | ||
133 | "id": "d34df1b1-5ebe-415e-8b43-80a15ef1e215", | 139 | "id": "d34df1b1-5ebe-415e-8b43-80a15ef1e215", | ||
134 | "name": "machine reading", | 140 | "name": "machine reading", | ||
135 | "state": "active", | 141 | "state": "active", | ||
136 | "vocabulary_id": null | 142 | "vocabulary_id": null | ||
137 | }, | 143 | }, | ||
138 | { | 144 | { | ||
139 | "display_name": "natural language processing", | 145 | "display_name": "natural language processing", | ||
140 | "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c", | 146 | "id": "8af9c93a-1d87-41e0-83d9-f5d01a2bbd0c", | ||
141 | "name": "natural language processing", | 147 | "name": "natural language processing", | ||
142 | "state": "active", | 148 | "state": "active", | ||
143 | "vocabulary_id": null | 149 | "vocabulary_id": null | ||
144 | }, | 150 | }, | ||
145 | { | 151 | { | ||
146 | "display_name": "open research knowledge graph", | 152 | "display_name": "open research knowledge graph", | ||
147 | "id": "c9fb26fb-f92f-4740-899e-290c1a384971", | 153 | "id": "c9fb26fb-f92f-4740-899e-290c1a384971", | ||
148 | "name": "open research knowledge graph", | 154 | "name": "open research knowledge graph", | ||
149 | "state": "active", | 155 | "state": "active", | ||
150 | "vocabulary_id": null | 156 | "vocabulary_id": null | ||
151 | }, | 157 | }, | ||
152 | { | 158 | { | ||
153 | "display_name": "orkg", | 159 | "display_name": "orkg", | ||
154 | "id": "a029b5df-5c95-4e99-94f3-1d9e2fbf1fd0", | 160 | "id": "a029b5df-5c95-4e99-94f3-1d9e2fbf1fd0", | ||
155 | "name": "orkg", | 161 | "name": "orkg", | ||
156 | "state": "active", | 162 | "state": "active", | ||
157 | "vocabulary_id": null | 163 | "vocabulary_id": null | ||
158 | }, | 164 | }, | ||
159 | { | 165 | { | ||
160 | "display_name": "pilot annotation", | 166 | "display_name": "pilot annotation", | ||
161 | "id": "33d81870-19c7-4aea-9ba6-76c17255b905", | 167 | "id": "33d81870-19c7-4aea-9ba6-76c17255b905", | ||
162 | "name": "pilot annotation", | 168 | "name": "pilot annotation", | ||
163 | "state": "active", | 169 | "state": "active", | ||
164 | "vocabulary_id": null | 170 | "vocabulary_id": null | ||
165 | }, | 171 | }, | ||
166 | { | 172 | { | ||
167 | "display_name": "scholarly knowledge graph", | 173 | "display_name": "scholarly knowledge graph", | ||
168 | "id": "cad5b92d-5dd7-4e88-ab94-cf3dc6cb6594", | 174 | "id": "cad5b92d-5dd7-4e88-ab94-cf3dc6cb6594", | ||
169 | "name": "scholarly knowledge graph", | 175 | "name": "scholarly knowledge graph", | ||
170 | "state": "active", | 176 | "state": "active", | ||
171 | "vocabulary_id": null | 177 | "vocabulary_id": null | ||
172 | }, | 178 | }, | ||
173 | { | 179 | { | ||
174 | "display_name": "semantic web", | 180 | "display_name": "semantic web", | ||
175 | "id": "cc98f198-dc4f-47f2-87b4-9ee665b8dfd8", | 181 | "id": "cc98f198-dc4f-47f2-87b4-9ee665b8dfd8", | ||
176 | "name": "semantic web", | 182 | "name": "semantic web", | ||
177 | "state": "active", | 183 | "state": "active", | ||
178 | "vocabulary_id": null | 184 | "vocabulary_id": null | ||
179 | } | 185 | } | ||
180 | ], | 186 | ], | ||
181 | "terms_of_usage": "Yes", | 187 | "terms_of_usage": "Yes", | ||
182 | "title": "NLPContributionGraph Trial Dataset", | 188 | "title": "NLPContributionGraph Trial Dataset", | ||
183 | "type": "vdataset", | 189 | "type": "vdataset", | ||
184 | "url": | 190 | "url": | ||
185 | "https://data.uni-hannover.de/dataset/nlpcontributions-pilot-dataset", | 191 | "https://data.uni-hannover.de/dataset/nlpcontributions-pilot-dataset", | ||
186 | "version": "2.0" | 192 | "version": "2.0" | ||
187 | } | 193 | } |