File size: 29,562 Bytes
9999db9
b7fbd2a
 
8c3bdec
 
 
 
 
 
 
 
 
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165989e
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165989e
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165989e
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165989e
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165989e
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9999db9
 
b7fbd2a
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
{
  "overview": {
    "section-title": "Dataset Overview",
    "what": {
      "section-title": "What is this dataset?",
      "dataset": {
        "title": "Summary",
        "info": "Provide a summary of this dataset in 3-4 sentences.",
        "flags": [
        ],
        "scope": "telescope"
      }
    },
    "where": {
      "section-title": "Where to find the Data and its Documentation",
      "website": {
        "title": "Webpage",
        "info": "What is the webpage for the dataset (if it exists)?",
        "flags": [
        ],
        "scope": "telescope"
      },
      "data-url": {
        "title": "Download",
        "info": "What is the link to where the original dataset is hosted?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "paper-url": {
        "title": "Paper",
        "info": "What is the link to the paper describing the dataset (open access preferred)?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "paper-bibtext": {
        "title": "BibTex",
        "info": "Provide the BibTex-formatted reference for the dataset. Please use the correct published version (ACL anthology, etc.) instead of google scholar created Bibtex.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "contact-name": {
        "title": "Contact Name",
        "info": "If known, provide the name of at least one person the reader can contact for questions about the dataset.",
        "flags": [
          "quick"
        ],
        "scope": "periscope"
      },
      "contact-email": {
        "title": "Contact Email",
        "info": "If known, provide the email of at least one person the reader can contact for questions about the dataset.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "has-leaderboard": {
        "title": "Has a Leaderboard?",
        "info": "Does the dataset have an active leaderboard?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "leaderboard-url": {
        "title": "Leaderboard Link",
        "info": "Provide a link to the leaderboard.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "leaderboard-description": {
        "title": "Leaderboard Details",
        "info": "Briefly describe how the leaderboard evaluates models.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "languages": {
      "section-title": "Languages and Intended Use",
      "is-multilingual": {
        "title": "Multilingual?",
        "info": "Is the dataset multilingual?",
        "flags": [
          "quick"
        ],
        "scope": "telescope"
      },
      "language-dialects": {
        "title": "Covered Dialects",
        "info": "What dialects are covered? Are there multiple dialects per language?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "language-names": {
        "title": "Covered Languages",
        "info": "What languages/dialects are covered in the dataset?",
        "flags": [
          "quick"
        ],
        "scope": "telescope"
      },
      "language-speakers": {
        "title": "Whose Language?",
        "info": "Whose language is in the dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "license": {
        "title": "License",
        "info": "What is the license of the dataset?",
        "flags": [
          "quick"
        ],
        "scope": "telescope"
      },
      "task-other": {
        "title": "Primary Task",
        "info": "What is the primary task?",
        "flags": [
          "quick"
        ],
        "scope": "periscope"
      },
      "intended-use": {
        "title": "Intended Use",
        "info": "What is the intended use of the dataset?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "license-other": {
        "title": "Add. License Info",
        "info": "What is the 'other' license of the dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "task": {
        "title": "Primary Task",
        "info": "What primary task does the dataset support?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "communicative": {
        "title": "Communicative Goal",
        "info": "Provide a short description of the communicative goal of a model trained for this task on this dataset.",
        "flags": [
          "quick"
        ],
        "scope": "periscope"
      }
    },
    "credit": {
      "section-title": "Credit",
      "organization-type": {
        "title": "Curation Organization Type(s)",
        "info": "In what kind of organization did the dataset curation happen?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "organization-names": {
        "title": "Curation Organization(s)",
        "info": "Name the organization(s).",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "creators": {
        "title": "Dataset Creators",
        "info": "Who created the original dataset? List the people involved in collecting the dataset and their affiliation(s).",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "funding": {
        "title": "Funding",
        "info": "Who funded the data creation?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "gem-added-by": {
        "title": "Who added the Dataset to GEM?",
        "info": "Who contributed to the data card and adding the dataset to GEM? List the people+affiliations involved in creating this data card and who helped integrate this dataset into GEM.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "structure": {
      "section-title": "Dataset Structure",
      "data-fields": {
        "title": "Data Fields",
        "info": "List and describe the fields present in the dataset.",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "structure-description": {
        "title": "Reason for Structure",
        "info": "How was the dataset structure determined?",
        "flags": [
        ],
        "scope": "microscope"
      },
      "structure-labels": {
        "title": "How were labels chosen?",
        "info": "How were the labels chosen?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "structure-example": {
        "title": "Example Instance",
        "info": "Provide a JSON formatted example of a typical instance in the dataset.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "structure-splits": {
        "title": "Data Splits",
        "info": "Describe and name the splits in the dataset if there are more than one.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "structure-splits-criteria": {
        "title": "Splitting Criteria",
        "info": "Describe any criteria for splitting the data, if used. If there are differences between the splits (e.g., if the training annotations are machine-generated and the dev and test ones are created by humans, or if different numbers of annotators contributed to each example), describe them here.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "structure-outlier": {
        "title": "",
        "info": "What does an outlier of the dataset in terms of length/perplexity/embedding look like?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    }
  },
  "gem": {
    "section-title": "Dataset in GEM",
    "rationale": {
      "section-title": "Rationale for Inclusion in GEM",
      "contribution": {
        "title": "Why is the Dataset in GEM?",
        "info": "What does this dataset contribute toward better generation evaluation and why is it part of GEM?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "sole-task-dataset": {
        "title": "Similar Datasets",
        "info": "Do other datasets for the high level task exist?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "sole-language-task-dataset": {
        "title": "Unique Language Coverage",
        "info": "Does this dataset cover other languages than other datasets for the same task?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "distinction-description": {
        "title": "Difference from other GEM datasets",
        "info": "What else sets this dataset apart from other similar datasets in GEM?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "model-ability": {
        "title": "Ability that the Dataset measures",
        "info": "What aspect of model ability can be measured with this dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    },
    "curation": {
      "section-title": "GEM-Specific Curation",
      "has-additional-curation": {
        "title": "Modificatied for GEM?",
        "info": "Has the GEM version of the dataset been modified in any way (data, processing, splits) from the original curated data?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "modification-types": {
        "title": "GEM Modifications",
        "info": "What changes have been made to he original dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "modification-description": {
        "title": "Modification Details",
        "info": "For each of these changes, described them in more details and provided the intended purpose of the modification",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "has-additional-splits": {
        "title": "Additional Splits?",
        "info": "Does GEM provide additional splits to the dataset?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "additional-splits-description": {
        "title": "Split Information",
        "info": "Describe how the new splits were created",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "additional-splits-capacicites": {
        "title": "Split Motivation",
        "info": "What aspects of the model's generation capacities were the splits created to test?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    },
    "starting": {
      "section-title": "Getting Started with the Task",
      "research-pointers": {
        "title": "Pointers to Resources",
        "info": "Getting started with in-depth research on the task. Add relevant pointers to resources that researchers can consult when they want to get started digging deeper into the task.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "technical-terms": {
        "title": "Technical Terms",
        "info": "Technical terms used in this card and the dataset and their definitions",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    }
  },
  "results": {
    "section-title": "Previous Results",
    "results": {
      "section-title": "Previous Results",
      "model-abilities": {
        "title": "Measured Model Abilities",
        "info": "What aspect of model ability can be measured with this dataset?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "metrics": {
        "title": "Metrics",
        "info": "What metrics are typically used for this task?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "other-metrics-definitions": {
        "title": "Other Metrics",
        "info": "Definitions of other metrics",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "original-evaluation": {
        "title": "Proposed Evaluation",
        "info": "List and describe the purpose of the metrics and evaluation methodology (including human evaluation) that the dataset creators used when introducing this task.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "has-previous-results": {
        "title": "Previous results available?",
        "info": "Are previous results available?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "current-evaluation": {
        "title": "Other Evaluation Approaches",
        "info": "What evaluation approaches have others used?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "previous-results": {
        "title": "Relevant Previous Results",
        "info": "What are the most relevant previous results for this task/dataset?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    }
  },
  "curation": {
    "section-title": "Dataset Curation",
    "original": {
      "section-title": "Original Curation",
      "rationale": {
        "title": "Original Curation Rationale",
        "info": "Original curation rationale",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "communicative": {
        "title": "Communicative Goal",
        "info": "What was the communicative goal?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "is-aggregated": {
        "title": "Sourced from Different Sources",
        "info": "Is the dataset aggregated from different data sources?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "aggregated-sources": {
        "title": "Source Details",
        "info": "List the sources (one per line)",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    },
    "language": {
      "section-title": "Language Data",
      "obtained": {
        "title": "How was Language Data Obtained?",
        "info": "How was the language data obtained?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "found": {
        "title": "Where was it found?",
        "info": "If found, where from?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "crowdsourced": {
        "title": "Where was it crowdsourced?",
        "info": "If crowdsourced, where from?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "created": {
        "title": "Creation Process",
        "info": "If created for the dataset, describe the creation process.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "machine-generated": {
        "title": "Generation Method Link",
        "info": "If text was machine-generated for the dataset, provide a link to the generation method if available (N/A otherwise).",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "producers-description": {
        "title": "Language Producers",
        "info": "What further information do we have on the language producers?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "topics": {
        "title": "Topics Covered",
        "info": "Does the language in the dataset focus on specific topics? How would you describe them?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "validated": {
        "title": "Data Validation",
        "info": "Was the text validated by a different worker or a data curator?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "pre-processed": {
        "title": "Data Preprocessing",
        "info": "How was the text data pre-processed? (Enter N/A if the text was not pre-processed)",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "is-filtered": {
        "title": "Was Data Filtered?",
        "info": "Were text instances selected or filtered?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "filtered-criteria": {
        "title": "Filter Criteria",
        "info": "What were the selection criteria?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "annotations": {
      "section-title": "Structured Annotations",
      "origin": {
        "title": "Additional Annotations?",
        "info": "Does the dataset have additional annotations for each instance?",
        "flags": [
          "quick"
        ],
        "scope": "telescope"
      },
      "rater-number": {
        "title": "Number of Raters",
        "info": "What is the number of raters",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "rater-qualifications": {
        "title": "Rater Qualifications",
        "info": "Describe the qualifications required of an annotator.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "rater-training-num": {
        "title": "Raters per Training Example",
        "info": "How many annotators saw each training example?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "rater-test-num": {
        "title": "Raters per Test Example",
        "info": "How many annotators saw each test example?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "rater-annotation-service-bool": {
        "title": "Annotation Service?",
        "info": "Was an annotation service used?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "rater-annotation-service": {
        "title": "Which Annotation Service",
        "info": "Which annotation services were used?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "values": {
        "title": "Annotation Values",
        "info": "Purpose and values for each annotation",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "quality-control": {
        "title": "Any Quality Control?",
        "info": "Quality control measures?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "quality-control-details": {
        "title": "Quality Control Details",
        "info": "Describe the quality control measures that were taken.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "consent": {
      "section-title": "Consent",
      "has-consent": {
        "title": "Any Consent Policy?",
        "info": "Was there a consent policy involved when gathering the data?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "consent-policy": {
        "title": "Consent Policy Details",
        "info": "What was the consent policy?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "consent-other": {
        "title": "Other Consented Downstream Use",
        "info": "What other downstream uses of the data did the original data creators and the data curators consent to?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "no-consent-justification": {
        "title": "Justification for Using the Data",
        "info": "If not, what is the justification for reusing the data?",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "pii": {
      "section-title": "Private Identifying Information (PII)",
      "has-pii": {
        "title": "Contains PII?",
        "info": "Does the source language data likely contain Personal Identifying Information about the data creators or subjects?",
        "flags": [
          "quick"
        ],
        "scope": "telescope"
      },
      "no-pii-justification": {
        "title": "Justification for no PII",
        "info": "Provide a justification for selecting `no PII` above.",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "pii-categories": {
        "title": "Categories of PII",
        "info": "What categories of PII are present or suspected in the data?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "is-pii-identified": {
        "title": "Any PII Identification?",
        "info": "Did the curators use any automatic/manual method to identify PII in the dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "pii-identified-method": {
        "title": "PII Identification Details",
        "info": "Describe the method used to identify PII in the dataset.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "is-pii-replaced": {
        "title": "Any Anonymization?",
        "info": "Was the PII pseudonymized/handled somehow?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "pii-replaced-method": {
        "title": "Anonymization Details",
        "info": "Describe the methods that were used to process the PII.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "maintenance": {
      "section-title": "Maintenance",
      "has-maintenance": {
        "title": "Any Maintenance Plan?",
        "info": "Does the original dataset have a maintenance plan?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "description": {
        "title": "Maintenance Plan Details",
        "info": "Describe the original dataset's maintenance plan.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "contact": {
        "title": "Maintainer Contact Information",
        "info": "Provide contact information of a person responsible for the dataset maintenance",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "contestation-mechanism": {
        "title": "Any Contestation Mechanism?",
        "info": "Does the maintenance plan include a contestation mechanism allowing individuals to request removal fo content?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "contestation-description": {
        "title": "Contestation Mechanism Details",
        "info": "Describe the contestation mechanism",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "contestation-link": {
        "title": "Contestation Form Link",
        "info": "Provide the form link or contact information",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    }
  },
  "context": {
    "section-title": "Broader Social Context",
    "previous": {
      "section-title": "Previous Work on the Social Impact of the Dataset",
      "is-deployed": {
        "title": "Usage of Models based on the Data",
        "info": "Are you aware of cases where models trained on the task featured in this dataset ore related tasks have been used in automated systems?",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "described-risks": {
        "title": "Social Impact Observations",
        "info": "Did any of these previous uses result in observations about the social impact of the systems? In particular, has there been work outlining the risks and limitations of the system? Provide links and descriptions here.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "changes-from-observation": {
        "title": "Changes as Consequence of Social Impact",
        "info": "Have any changes been made to the dataset as a result of these observations?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    },
    "underserved": {
      "section-title": "Impact on Under-Served Communities",
      "helps-underserved": {
        "title": "Addresses needs of underserved Communities?",
        "info": "Does this dataset address the needs of communities that are traditionally underserved in language technology, and particularly language generation technology? Communities may be underserved for exemple because their language, language variety, or social or geographical context is underepresented in NLP and NLG resources (datasets and models).",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "underserved-description": {
        "title": "Details on how Dataset Addresses the Needs",
        "info": "Describe how this dataset addresses the needs of underserved communities.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "biases": {
      "section-title": "Discussion of Biases",
      "has-biases": {
        "title": "Any Documented Social Biases?",
        "info": "Are there documented social biases in the dataset? Biases in this context are variations in the ways members of different social categories are represented that can have harmful downstream consequences for members of the more disadvantaged group.",
        "flags": [
          ""
        ],
        "scope": "telescope"
      },
      "bias-analyses": {
        "title": "Links and Summaries of Analysis Work",
        "info": "Provide links to and summaries of works analyzing these biases.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "speaker-distibution": {
        "title": "Are the Language Producers Representative of the Language?",
        "info": "Does the distribution of language producers in the dataset accurately represent the full distribution of speakers of the language world-wide? If not, how does it differ?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      }
    }
  },
  "considerations": {
    "section-title": "Considerations for Using the Data",
    "pii": {
      "section-title": "PII Risks and Liability",
      "risks-description": {
        "title": "Potential PII Risk",
        "info": "Considering your answers to the PII part of the Data Curation Section, describe any potential privacy to the data subjects and creators risks when using the dataset.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "licenses": {
      "section-title": "Licenses",
      "dataset-restrictions": {
        "title": "Copyright Restrictions on the Dataset",
        "info": "Based on your answers in the Intended Use part of the Data Overview Section, which of the following best describe the copyright and licensing status of the dataset?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "dataset-restrictions-other": {
        "title": "Copyright Restriction - Elaboration",
        "info": "You selected `other` for the dataset licensing status, please elaborate here:",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "data-copyright": {
        "title": "Copyright Restrictions on the Language Data",
        "info": "Based on your answers in the Language part of the Data Curation Section, which of the following best describe the copyright and licensing status of the underlying language data?",
        "flags": [
          ""
        ],
        "scope": "periscope"
      },
      "data-copyright-other": {
        "title": "Source Data Copyright Restriction - Elaboration",
        "info": "You selected `other` for the source data licensing status, please elaborate here:",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    },
    "limitations": {
      "section-title": "Known Technical Limitations",
      "data-technical-limitations": {
        "title": "Technical Limitations",
        "info": "Describe any known technical limitations, such as spurrious correlations, train/test overlap, annotation biases, or mis-annotations, and cite the works that first identified these limitations when possible.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "data-unsuited-applications": {
        "title": "Unsuited Applications",
        "info": "When using a model trained on this dataset in a setting where users or the public may interact with its predictions, what are some pitfalls to look out for? In particular, describe some applications of the general task featured in this dataset that its curation or properties make it less suitable for.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      },
      "data-discouraged-use": {
        "title": "Discouraged Use Cases",
        "info": "What are some discouraged use cases of a model trained to maximize the proposed metrics on this dataset? In particular, think about settings where decisions made by a model that performs reasonably well on the metric my still have strong negative consequences for user or members of the public.",
        "flags": [
          ""
        ],
        "scope": "microscope"
      }
    }
  }
}