-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathtasks_metadata.py
1278 lines (1261 loc) · 53.7 KB
/
tasks_metadata.py
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
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import datasets
from mteb import TaskMetadata
import pandas as pd
from tabulate import tabulate
_MASSIVE_LANGUAGES = {
"af": ["afr-Latn"],
"am": ["amh-Ethi"],
"ar": ["ara-Arab"],
"az": ["aze-Latn"],
"bn": ["ben-Beng"],
"cy": ["cym-Latn"],
"da": ["dan-Latn"],
"de": ["deu-Latn"],
"el": ["ell-Grek"],
"en": ["eng-Latn"],
"es": ["spa-Latn"],
"fa": ["fas-Arab"],
"fi": ["fin-Latn"],
"fr": ["fra-Latn"],
"he": ["heb-Hebr"],
"hi": ["hin-Deva"],
"hu": ["hun-Latn"],
"hy": ["hye-Armn"],
"id": ["ind-Latn"],
"is": ["isl-Latn"],
"it": ["ita-Latn"],
"ja": ["jpn-Jpan"],
"jv": ["jav-Latn"],
"ka": ["kat-Geor"],
"km": ["khm-Khmr"],
"kn": ["kan-Knda"],
"ko": ["kor-Kore"],
"lv": ["lav-Latn"],
"ml": ["mal-Mlym"],
"mn": ["mon-Cyrl"],
"ms": ["msa-Latn"],
"my": ["mya-Mymr"],
"nb": ["nob-Latn"],
"nl": ["nld-Latn"],
"pl": ["pol-Latn"],
"pt": ["por-Latn"],
"ro": ["ron-Latn"],
"ru": ["rus-Cyrl"],
"sl": ["slv-Latn"],
"sq": ["sqi-Latn"],
"sv": ["swe-Latn"],
"sw": ["swa-Latn"],
"ta": ["tam-Taml"],
"te": ["tel-Telu"],
"th": ["tha-Thai"],
"tl": ["tgl-Latn"],
"tr": ["tur-Latn"],
"ur": ["urd-Arab"],
"vi": ["vie-Latn"],
"zh-CN": ["cmo-Hans"],
"zh-TW": ["cmo-Hant"],
}
_STS22_LANGUAGES = {
"en": ["eng-Latn"],
"de": ["deu-Latn"],
"es": ["spa-Latn"],
"pl": ["pol-Latn"],
"tr": ["tur-Latn"],
"ar": ["ara-Arab"],
"ru": ["rus-Cyrl"],
"zh": ["cmn-Hans"],
"fr": ["fra-Latn"],
"de-en": ["deu-Latn", "eng-Latn"],
"es-en": ["spa-Latn", "eng-Latn"],
"it": ["ita-Latn"],
"pl-en": ["pol-Latn", "eng-Latn"],
"zh-en": ["cmn-Hans", "eng-Latn"],
"es-it": ["spa-Latn", "ita-Latn"],
"de-fr": ["deu-Latn", "fra-Latn"],
"de-pl": ["deu-Latn", "pol-Latn"],
"fr-pl": ["fra-Latn", "pol-Latn"],
}
tasks_metadata = {
"CBD": TaskMetadata(
name="CBD",
description="Polish Tweets annotated for cyberbullying detection. Creation procedure: [] #unbalanced",
reference="http://2019.poleval.pl/files/poleval2019.pdf",
dataset={
"path": "PL-MTEB/cbd",
"revision": "36ddb419bcffe6a5374c3891957912892916f28d",
},
type="Classification",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Social"],
task_subtypes=None,
license="bsd-3-clause",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@proceedings{ogr:kob:19:poleval,
editor = {Maciej Ogrodniczuk and Łukasz Kobyliński},
title = {{Proceedings of the PolEval 2019 Workshop}},
year = {2019},
address = {Warsaw, Poland},
publisher = {Institute of Computer Science, Polish Academy of Sciences},
url = {http://2019.poleval.pl/files/poleval2019.pdf},
isbn = "978-83-63159-28-3"}
}""",
n_samples={"train": 10000, "test": 1000},
avg_character_length={"train": 95.3, "test": 93.2},
),
"PolEmo2.0-IN": TaskMetadata(
name="PolEmo2.0-IN",
description="A collection of Polish online reviews from four domains: medicine, hotels, products and "
"school. The PolEmo2.0-IN task is to predict the sentiment of in-domain (medicine and hotels) reviews. #unbalanced",
reference="https://aclanthology.org/K19-1092.pdf",
dataset={
"path": "PL-MTEB/polemo2_in",
"revision": "d90724373c70959f17d2331ad51fb60c71176b03",
},
type="Classification",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Reviews"],
task_subtypes=None,
license="cc-by-nc-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{kocon-etal-2019-multi,
title = "Multi-Level Sentiment Analysis of {P}ol{E}mo 2.0: Extended Corpus of Multi-Domain Consumer Reviews",
author = "Koco{\'n}, Jan and
Mi{\l}kowski, Piotr and
Za{\'s}ko-Zieli{\'n}ska, Monika",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1092",
doi = "10.18653/v1/K19-1092",
pages = "980--991",
abstract = "In this article we present an extended version of PolEmo {--} a corpus of consumer reviews from 4 domains: medicine, hotels, products and school. Current version (PolEmo 2.0) contains 8,216 reviews having 57,466 sentences. Each text and sentence was manually annotated with sentiment in 2+1 scheme, which gives a total of 197,046 annotations. We obtained a high value of Positive Specific Agreement, which is 0.91 for texts and 0.88 for sentences. PolEmo 2.0 is publicly available under a Creative Commons copyright license. We explored recent deep learning approaches for the recognition of sentiment, such as Bi-directional Long Short-Term Memory (BiLSTM) and Bidirectional Encoder Representations from Transformers (BERT).",
}""",
n_samples={"train": 5780, "test": 722},
avg_character_length={"train": 738.3, "test": 741.4},
),
"PolEmo2.0-OUT": TaskMetadata(
name="PolEmo2.0-OUT",
description="A collection of Polish online reviews from four domains: medicine, hotels, products and "
"school. The PolEmo2.0-OUT task is to predict the sentiment of out-of-domain (products and "
"school) reviews using models train on reviews from medicine and hotels domains. #unbalanced",
reference="https://aclanthology.org/K19-1092.pdf",
dataset={
"path": "PL-MTEB/polemo2_out",
"revision": "6a21ab8716e255ab1867265f8b396105e8aa63d4",
},
type="Classification",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Reviews"],
task_subtypes=None,
license="cc-by-nc-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=None,
n_samples={"train": 5780, "test": 722},
avg_character_length={"train": 740.3, "test": 756.2},
),
"AllegroReviews": TaskMetadata(
name="AllegroReviews",
description="A Polish dataset for sentiment classification on reviews from e-commerce marketplace Allegro. #unbalanced",
reference="https://aclanthology.org/2020.acl-main.111.pdf",
dataset={
"path": "PL-MTEB/allegro-reviews",
"revision": "b89853e6de927b0e3bfa8ecc0e56fe4e02ceafc6",
},
type="Classification",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Reviews"],
task_subtypes=None,
license="cc-by-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=None,
n_samples={"train": 9580, "test": 1006},
avg_character_length={"train": 475.6, "test": 477.2},
),
"PAC": TaskMetadata(
name="PAC",
description="Polish Abusive Clauses Dataset #unbalanced",
reference="https://arxiv.org/pdf/2211.13112.pdf",
dataset={
"path": "laugustyniak/abusive-clauses-pl",
"revision": "fc69d1c153a8ccdcf1eef52f4e2a27f88782f543",
},
type="Classification",
category="p2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Legal"],
task_subtypes=None,
license="cc-by-nc-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=None,
n_samples={"train": 4284, "test": 3453},
avg_character_length={"train": 182.5, "test": 185.3},
),
"MassiveIntentClassification": TaskMetadata(
name="MassiveIntentClassification",
dataset={
"path": "mteb/amazon_massive_intent",
"revision": "4672e20407010da34463acc759c162ca9734bca6",
},
description="MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages #unbalanced",
reference="https://arxiv.org/abs/2204.08582#:~:text=MASSIVE%20contains%201M%20realistic%2C%20parallel,diverse%20languages%20from%2029%20genera.",
category="s2s",
type="Classification",
eval_splits=["validation", "test"],
eval_langs=_MASSIVE_LANGUAGES,
main_score="accuracy",
date=None,
form=None,
domains=["Spoken"],
task_subtypes=None,
license="cc-by-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{fitzgerald2022massive,
title={MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages},
author={Jack FitzGerald and Christopher Hench and Charith Peris and Scott Mackie and Kay Rottmann and Ana Sanchez and Aaron Nash and Liam Urbach and Vishesh Kakarala and Richa Singh and Swetha Ranganath and Laurie Crist and Misha Britan and Wouter Leeuwis and Gokhan Tur and Prem Natarajan},
year={2022},
eprint={2204.08582},
archivePrefix={arXiv},
primaryClass={cs.CL}
}""",
n_samples={"train": 11500, "validation": 2033, "test": 2974},
avg_character_length={"train": 34.5, "validation": 34.8, "test": 34.6},
),
"MassiveScenarioClassification": TaskMetadata(
name="MassiveScenarioClassification",
dataset={
"path": "mteb/amazon_massive_scenario",
"revision": "fad2c6e8459f9e1c45d9315f4953d921437d70f8",
},
description="MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages #unbalanced",
reference="https://arxiv.org/abs/2204.08582#:~:text=MASSIVE%20contains%201M%20realistic%2C%20parallel,diverse%20languages%20from%2029%20genera.",
category="s2s",
type="Classification",
eval_splits=["validation", "test"],
eval_langs=_MASSIVE_LANGUAGES,
main_score="accuracy",
date=None,
form=None,
domains=["Spoken"],
task_subtypes=None,
license="cc-by-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{fitzgerald2022massive,
title={MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages},
author={Jack FitzGerald and Christopher Hench and Charith Peris and Scott Mackie and Kay Rottmann and Ana Sanchez and Aaron Nash and Liam Urbach and Vishesh Kakarala and Richa Singh and Swetha Ranganath and Laurie Crist and Misha Britan and Wouter Leeuwis and Gokhan Tur and Prem Natarajan},
year={2022},
eprint={2204.08582},
archivePrefix={arXiv},
primaryClass={cs.CL}
}""",
n_samples={"train": 11500, "validation": 2033, "test": 2974},
avg_character_length={"train": 34.5, "validation": 34.8, "test": 34.6},
),
"SciField": TaskMetadata(
name="SciField",
description="Based on the paragraph from the coursebook, identify the scientific field from which it comes. "
"Available fields are: chemistry, physics, mathematics, geology and social science. #unbalanced",
reference="https://huggingface.co/datasets/rafalposwiata/open-coursebooks-pl",
dataset={
"path": "PL-MTEB/scifield",
"revision": "8064b4442da038aa0482a2542370f9a2441cc50a",
},
type="Classification",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="accuracy",
date=None,
form=None,
domains=["Academic"],
task_subtypes=None,
license="cc-by-sa-4.0",
socioeconomic_status="high",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="",
n_samples={"train": 5751, "test": 1438},
avg_character_length={"train": 431.6, "test": 430.4},
),
"EightTagsClustering": TaskMetadata(
name="EightTagsClustering",
description="Clustering of headlines from social media posts in Polish belonging to 8 categories: film, history, "
"food, medicine, motorization, work, sport and technology.",
reference="https://aclanthology.org/2020.lrec-1.207.pdf",
dataset={
"path": "PL-MTEB/8tags-clustering",
"revision": "78b962b130c6690659c65abf67bf1c2f030606b6",
},
type="Clustering",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="v_measure",
date=("2019-01-01", "2020-05-01"),
form=["written"],
domains=["Social"],
task_subtypes=["Topic classification", "Thematic clustering"],
license="GPL-3.0",
socioeconomic_status="mixed",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="""@inproceedings{dadas-etal-2020-evaluation,
title = "Evaluation of Sentence Representations in {P}olish",
author = "Dadas, Slawomir and
Pere{\l}kiewicz, Micha{\l} and
Po{\'s}wiata, Rafa{\l}",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.207",
pages = "1674--1680",
abstract = "Methods for learning sentence representations have been actively developed in recent years. However, the lack of pre-trained models and datasets annotated at the sentence level has been a problem for low-resource languages such as Polish which led to less interest in applying these methods to language-specific tasks. In this study, we introduce two new Polish datasets for evaluating sentence embeddings and provide a comprehensive evaluation of eight sentence representation methods including Polish and multilingual models. We consider classic word embedding models, recently developed contextual embeddings and multilingual sentence encoders, showing strengths and weaknesses of specific approaches. We also examine different methods of aggregating word vectors into a single sentence vector.",
language = "English",
ISBN = "979-10-95546-34-4",
}""",
n_samples={"test": 49373},
avg_character_length={"test": 78.23}
),
"PlscClusteringS2S": TaskMetadata(
name="PlscClusteringS2S",
description="Clustering of Polish article titles from Library of Science (https://bibliotekanauki.pl/), either "
"on the scientific field or discipline.",
reference="https://huggingface.co/datasets/rafalposwiata/plsc",
dataset={
"path": "PL-MTEB/plsc-clustering-s2s",
"revision": "39bcadbac6b1eddad7c1a0a176119ce58060289a",
},
type="Clustering",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="v_measure",
date=("2022-04-04", "2023-09-12"),
form=["written"],
domains=["Academic"],
task_subtypes=["Topic classification"],
license="cc0-1.0",
socioeconomic_status="high",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="",
n_samples={"test": 17534},
avg_character_length={"test": 84.34},
),
"PlscClusteringP2P": TaskMetadata(
name="PlscClusteringP2P",
description="Clustering of Polish article titles+abstracts from Library of Science "
"(https://bibliotekanauki.pl/), either on the scientific field or discipline.",
reference="https://huggingface.co/datasets/rafalposwiata/plsc",
dataset={
"path": "PL-MTEB/plsc-clustering-p2p",
"revision": "8436dd4c05222778013d6642ee2f3fa1722bca9b",
},
type="Clustering",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="v_measure",
date=("2022-04-04", "2023-09-12"),
form=["written"],
domains=["Academic"],
task_subtypes=["Topic classification"],
license="cc0-1.0",
socioeconomic_status="high",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="",
n_samples={"test": 17537},
avg_character_length={"test": 1023.21},
),
"WikinewsPlClusteringS2S": TaskMetadata(
name="WikinewsPlClusteringS2S",
description="",
reference="https://huggingface.co/datasets/rafalposwiata/wikinews-pl",
dataset={
"path": "PL-MTEB/wikinews-pl-clustering-s2s",
"revision": "2355f412aa5b735fc66cbfe8dff766c49fb45a5d",
},
type="Clustering",
category="s2s",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="v_measure",
date=("2020-01-01", "2024-06-05"),
form=["written"],
domains=["News"],
task_subtypes=["Topic classification"],
license="cc-by-2.5",
socioeconomic_status="high",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="",
n_samples={"test": 4477},
avg_character_length={"test": 60.18},
),
"WikinewsPlClusteringP2P": TaskMetadata(
name="WikinewsPlClusteringP2P",
description="",
reference="https://huggingface.co/datasets/rafalposwiata/wikinews-pl",
dataset={
"path": "PL-MTEB/wikinews-pl-clustering-p2p",
"revision": "8f10d8e9d094ff9f2a8e99e645ad22eb745eb3cf",
},
type="Clustering",
category="p2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="v_measure",
date=("2020-01-01", "2024-06-05"),
form=["written"],
domains=["News"],
task_subtypes=["Topic classification"],
license="cc-by-2.5",
socioeconomic_status="high",
annotations_creators="derived",
dialect=[],
text_creation="found",
bibtex_citation="",
n_samples={"test": 4477},
avg_character_length={"test": 1127.31},
),
"SICK-E-PL": TaskMetadata(
name="SICK-E-PL",
dataset={
"path": "PL-MTEB/sicke-pl-pairclassification",
"revision": "71bba34b0ece6c56dfcf46d9758a27f7a90f17e9",
},
description="Polish version of SICK dataset for textual entailment.",
reference="https://aclanthology.org/2020.lrec-1.207",
category="s2s",
type="PairClassification",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ap",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="cc-by-nc-sa-3.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{dadas-etal-2020-evaluation,
title = "Evaluation of Sentence Representations in {P}olish",
author = "Dadas, Slawomir and
Pere{\l}kiewicz, Micha{\l} and
Po{\'s}wiata, Rafa{\l}",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.207",
pages = "1674--1680",
abstract = "Methods for learning sentence representations have been actively developed in recent years. However, the lack of pre-trained models and datasets annotated at the sentence level has been a problem for low-resource languages such as Polish which led to less interest in applying these methods to language-specific tasks. In this study, we introduce two new Polish datasets for evaluating sentence embeddings and provide a comprehensive evaluation of eight sentence representation methods including Polish and multilingual models. We consider classic word embedding models, recently developed contextual embeddings and multilingual sentence encoders, showing strengths and weaknesses of specific approaches. We also examine different methods of aggregating word vectors into a single sentence vector.",
language = "English",
ISBN = "979-10-95546-34-4",
}""",
n_samples={"test": 1000},
avg_character_length={"test": 42.8},
),
"PPC": TaskMetadata(
name="PPC",
dataset={
"path": "PL-MTEB/ppc-pairclassification",
"revision": "2c7d2df57801a591f6b1e3aaf042e7a04ec7d9f2",
},
description="Polish Paraphrase Corpus",
reference="https://arxiv.org/pdf/2207.12759.pdf",
category="s2s",
type="PairClassification",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ap",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="cc-by-nc-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=None,
n_samples={"test": 1000},
avg_character_length={"test": 98.2},
),
"CDSC-E": TaskMetadata(
name="CDSC-E",
dataset={
"path": "PL-MTEB/cdsce-pairclassification",
"revision": "0a3d4aa409b22f80eb22cbf59b492637637b536d",
},
description="Compositional Distributional Semantics Corpus for textual entailment.",
reference="https://aclanthology.org/P17-1073.pdf",
category="s2s",
type="PairClassification",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ap",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="cc-by-nc-sa-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{wroblewska-krasnowska-kieras-2017-polish,
title = "{P}olish evaluation dataset for compositional distributional semantics models",
author = "Wr{\'o}blewska, Alina and
Krasnowska-Kiera{\'s}, Katarzyna",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1073",
doi = "10.18653/v1/P17-1073",
pages = "784--792",
abstract = "The paper presents a procedure of building an evaluation dataset. for the validation of compositional distributional semantics models estimated for languages other than English. The procedure generally builds on steps designed to assemble the SICK corpus, which contains pairs of English sentences annotated for semantic relatedness and entailment, because we aim at building a comparable dataset. However, the implementation of particular building steps significantly differs from the original SICK design assumptions, which is caused by both lack of necessary extraneous resources for an investigated language and the need for language-specific transformation rules. The designed procedure is verified on Polish, a fusional language with a relatively free word order, and contributes to building a Polish evaluation dataset. The resource consists of 10K sentence pairs which are human-annotated for semantic relatedness and entailment. The dataset may be used for the evaluation of compositional distributional semantics models of Polish.",
}""",
n_samples={"test": 4910},
avg_character_length={"test": 75.24},
),
"PSC": TaskMetadata(
name="PSC",
dataset={
"path": "PL-MTEB/psc-pairclassification",
"revision": "d05a294af9e1d3ff2bfb6b714e08a24a6cabc669",
},
description="Polish Summaries Corpus",
reference="http://www.lrec-conf.org/proceedings/lrec2014/pdf/1211_Paper.pdf",
category="s2s",
type="PairClassification",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ap",
date=None,
form=None,
domains=["News"],
task_subtypes=None,
license="cc-by-sa-3.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{ogrodniczuk-kopec-2014-polish,
title = "The {P}olish Summaries Corpus",
author = "Ogrodniczuk, Maciej and
Kope{\'c}, Mateusz",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1211_Paper.pdf",
pages = "3712--3715",
abstract = "This article presents the Polish Summaries Corpus, a new resource created to support the development and evaluation of the tools for automated single-document summarization of Polish. The Corpus contains a large number of manual summaries of news articles, with many independently created summaries for a single text. Such approach is supposed to overcome the annotator bias, which is often described as a problem during the evaluation of the summarization algorithms against a single gold standard. There are several summarizers developed specifically for Polish language, but their in-depth evaluation and comparison was impossible without a large, manually created corpus. We present in detail the process of text selection, annotation process and the contents of the corpus, which includes both abstract free-word summaries, as well as extraction-based summaries created by selecting text spans from the original document. Finally, we describe how that resource could be used not only for the evaluation of the existing summarization tools, but also for studies on the human summarization process in Polish language.",
}""",
n_samples={"test": 1080},
avg_character_length={"test": 647.8},
),
"ArguAna-PL": TaskMetadata(
name="ArguAna-PL",
description="ArguAna-PL",
reference="https://huggingface.co/datasets/clarin-knext/arguana-pl",
dataset={
"path": "clarin-knext/arguana-pl",
"revision": "63fc86750af76253e8c760fc9e534bbf24d260a2",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=['Web'],
task_subtypes=None,
license="CC-BY-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 1406, 'test_corpus': 8674},
avg_character_length={'test': 1224.8, 'test_corpus': 1036.7},
),
"DBPedia-PL": TaskMetadata(
name="DBPedia-PL",
description="DBpedia-Entity is a standard test collection for entity search over the DBpedia knowledge base",
reference="https://github.com/iai-group/DBpedia-Entity/",
dataset={
"path": "clarin-knext/dbpedia-pl",
"revision": "76afe41d9af165cc40999fcaa92312b8b012064a",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=['Encyclopaedic'],
task_subtypes=None,
license="CC-BY-SA-3.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{Hasibi:2017:DVT,
author = {Hasibi, Faegheh and Nikolaev, Fedor and Xiong, Chenyan and Balog, Krisztian and Bratsberg, Svein Erik and Kotov, Alexander and Callan, Jamie},
title = {DBpedia-Entity V2: A Test Collection for Entity Search},
booktitle = {Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval},
series = {SIGIR '17},
year = {2017},
pages = {1265--1268},
doi = {10.1145/3077136.3080751},
publisher = {ACM}
}""",
n_samples={'test': 467, 'test_corpus': 4635922},
avg_character_length={'test': 34.7, 'test_corpus': 291.3},
),
"FiQA-PL": TaskMetadata(
name="FiQA-PL",
description="Financial Opinion Mining and Question Answering",
reference="https://sites.google.com/view/fiqa/",
dataset={
"path": "clarin-knext/fiqa-pl",
"revision": "2e535829717f8bf9dc829b7f911cc5bbd4e6608e",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=['Web'],
task_subtypes=None,
license="Not specified",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@inproceedings{
thakur2021beir,
title={{BEIR}: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models},
author={Nandan Thakur and Nils Reimers and Andreas R{\"u}ckl{\'e} and Abhishek Srivastava and Iryna Gurevych},
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
year={2021},
url={https://openreview.net/forum?id=wCu6T5xFjeJ}
}""",
n_samples={'test': 6648, 'test_corpus': 57638},
avg_character_length={'test': 69.1, 'test_corpus': 795.2},
),
"HotpotQA-PL": TaskMetadata(
name="HotpotQA-PL",
description="HotpotQA is a question answering dataset featuring natural, multi-hop questions, with strong supervision for supporting facts to enable more explainable question answering systems.",
reference="https://hotpotqa.github.io/",
dataset={
"path": "clarin-knext/hotpotqa-pl",
"revision": "a0bd479ac97b4ccb5bd6ce320c415d0bb4beb907",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Encyclopaedic"],
task_subtypes=None,
license="CC-BY-SA-4.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 97852, 'test_corpus': 5233329},
avg_character_length={'test': 107.6, 'test_corpus': 271.7},
),
"MSMARCO-PL": TaskMetadata(
name="MSMARCO-PL",
description="MS MARCO is a collection of datasets focused on deep learning in search",
reference="https://microsoft.github.io/msmarco/",
dataset={
"path": "clarin-knext/msmarco-pl",
"revision": "8634c07806d5cce3a6138e260e59b81760a0a640",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="MIT",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=""""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 520362, 'test_corpus': 8841823},
avg_character_length={'test': 35.2, 'test_corpus': 349.4},
),
"NFCorpus-PL": TaskMetadata(
name="NFCorpus-PL",
description="NFCorpus: A Full-Text Learning to Rank Dataset for Medical Information Retrieval",
reference="https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/",
dataset={
"path": "clarin-knext/nfcorpus-pl",
"revision": "9a6f9567fda928260afed2de480d79c98bf0bec0",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Medical"],
task_subtypes=None,
license="Not specified",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 3237, 'test_corpus': 3633},
avg_character_length={'test': 24.6, 'test_corpus': 1554.3},
),
"NQ-PL": TaskMetadata(
name="NQ-PL",
description="Natural Questions: A Benchmark for Question Answering Research",
reference="https://ai.google.com/research/NaturalQuestions/",
dataset={
"path": "clarin-knext/nq-pl",
"revision": "f171245712cf85dd4700b06bef18001578d0ca8d",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="CC-BY-SA-3.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 3452, 'test_corpus': 2681468},
avg_character_length={'test': 48.3, 'test_corpus': 480.9},
),
"Quora-PL": TaskMetadata(
name="Quora-PL",
description="QuoraRetrieval is based on questions that are marked as duplicates on the Quora platform. Given a question, find other (duplicate) questions.",
reference="https://quoradata.quora.com/First-Quora-Dataset-Release-Question-Pairs",
dataset={
"path": "clarin-knext/quora-pl",
"revision": "0be27e93455051e531182b85e85e425aba12e9d4",
},
type="Retrieval",
category="s2s",
eval_splits=["validation", "test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Web"],
task_subtypes=None,
license="Not specified",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation=""""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 15000, 'test_corpus': 522931},
avg_character_length={'test': 54.6, 'test_corpus': 65.8},
),
"SCIDOCS-PL": TaskMetadata(
name="SCIDOCS-PL",
description="SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation.",
reference="https://allenai.org/data/scidocs",
dataset={
"path": "clarin-knext/scidocs-pl",
"revision": "45452b03f05560207ef19149545f168e596c9337",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Academic"],
task_subtypes=None,
license="GNU-3.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 1000, 'test_corpus': 25657},
avg_character_length={'test': 80.7, 'test_corpus': 1191.0},
),
"SciFact-PL": TaskMetadata(
name="SciFact-PL",
description="SciFact verifies scientific claims using evidence from the research literature containing scientific paper abstracts.",
reference="https://github.com/allenai/scifact",
dataset={
"path": "clarin-knext/scifact-pl",
"revision": "47932a35f045ef8ed01ba82bf9ff67f6e109207e",
},
type="Retrieval",
category="s2p",
eval_splits=["test"],
eval_langs=["pol-Latn"],
main_score="ndcg_at_10",
date=None,
form=None,
domains=["Academic"],
task_subtypes=None,
license="CC-BY-NC-2.0",
socioeconomic_status=None,
annotations_creators=None,
dialect=None,
text_creation=None,
bibtex_citation="""@misc{wojtasik2024beirpl,
title={BEIR-PL: Zero Shot Information Retrieval Benchmark for the Polish Language},
author={Konrad Wojtasik and Vadim Shishkin and Kacper Wołowiec and Arkadiusz Janz and Maciej Piasecki},
year={2024},
eprint={2305.19840},
archivePrefix={arXiv},
primaryClass={cs.IR}
}""",
n_samples={'test': 1109, 'test_corpus': 5183},
avg_character_length={'test': 93.9, 'test_corpus': 1450.6},
),
"TRECCOVID-PL": TaskMetadata(
name="TRECCOVID-PL",
description="TRECCOVID is an ad-hoc search challenge based on the COVID-19 dataset containing scientific articles related to the COVID-19 pandemic.",
reference="https://ir.nist.gov/covidSubmit/index.html",
dataset={
"path": "clarin-knext/trec-covid-pl",
"revision": "81bcb408f33366c2a20ac54adafad1ae7e877fdd",
},