metadata
model-index:
- name: karsar/paraphrase-multilingual-MiniLM-L12-hu-v2
results:
- dataset:
config: hun_Latn-hun_Latn
name: MTEB BelebeleRetrieval (hun_Latn-hun_Latn)
revision: 75b399394a9803252cfec289d103de462763db7c
split: test
type: facebook/belebele
metrics:
- type: main_score
value: 80.204
- type: map_at_1
value: 69.111
- type: map_at_10
value: 76.773
- type: map_at_100
value: 77.169
- type: map_at_1000
value: 77.173
- type: map_at_20
value: 77.033
- type: map_at_3
value: 75.333
- type: map_at_5
value: 76.19399999999999
- type: mrr_at_1
value: 69.11111111111111
- type: mrr_at_10
value: 76.77345679012352
- type: mrr_at_100
value: 77.16929744881674
- type: mrr_at_1000
value: 77.17269244765126
- type: mrr_at_20
value: 77.03286768605402
- type: mrr_at_3
value: 75.33333333333334
- type: mrr_at_5
value: 76.19444444444449
- type: nauc_map_at_1000_diff1
value: 80.43265248651925
- type: nauc_map_at_1000_max
value: 71.870230668987
- type: nauc_map_at_1000_std
value: -3.0084092423300604
- type: nauc_map_at_100_diff1
value: 80.42911054177607
- type: nauc_map_at_100_max
value: 71.86888714337594
- type: nauc_map_at_100_std
value: -3.0086379837670716
- type: nauc_map_at_10_diff1
value: 80.36522921472617
- type: nauc_map_at_10_max
value: 71.97959119190223
- type: nauc_map_at_10_std
value: -2.7429598598137104
- type: nauc_map_at_1_diff1
value: 83.07496179427446
- type: nauc_map_at_1_max
value: 70.1472835630915
- type: nauc_map_at_1_std
value: -4.892100745257178
- type: nauc_map_at_20_diff1
value: 80.4010557171958
- type: nauc_map_at_20_max
value: 71.9262402987486
- type: nauc_map_at_20_std
value: -2.855142719268829
- type: nauc_map_at_3_diff1
value: 80.21618957663902
- type: nauc_map_at_3_max
value: 72.32078865805673
- type: nauc_map_at_3_std
value: -3.307117509227628
- type: nauc_map_at_5_diff1
value: 80.25726339569668
- type: nauc_map_at_5_max
value: 71.96694381406756
- type: nauc_map_at_5_std
value: -2.835991564758579
- type: nauc_mrr_at_1000_diff1
value: 80.43265248651925
- type: nauc_mrr_at_1000_max
value: 71.870230668987
- type: nauc_mrr_at_1000_std
value: -3.0084092423300604
- type: nauc_mrr_at_100_diff1
value: 80.42911054177607
- type: nauc_mrr_at_100_max
value: 71.86888714337594
- type: nauc_mrr_at_100_std
value: -3.0086379837670716
- type: nauc_mrr_at_10_diff1
value: 80.36522921472617
- type: nauc_mrr_at_10_max
value: 71.97959119190223
- type: nauc_mrr_at_10_std
value: -2.7429598598137104
- type: nauc_mrr_at_1_diff1
value: 83.07496179427446
- type: nauc_mrr_at_1_max
value: 70.1472835630915
- type: nauc_mrr_at_1_std
value: -4.892100745257178
- type: nauc_mrr_at_20_diff1
value: 80.4010557171958
- type: nauc_mrr_at_20_max
value: 71.9262402987486
- type: nauc_mrr_at_20_std
value: -2.855142719268829
- type: nauc_mrr_at_3_diff1
value: 80.21618957663902
- type: nauc_mrr_at_3_max
value: 72.32078865805673
- type: nauc_mrr_at_3_std
value: -3.307117509227628
- type: nauc_mrr_at_5_diff1
value: 80.25726339569668
- type: nauc_mrr_at_5_max
value: 71.96694381406756
- type: nauc_mrr_at_5_std
value: -2.835991564758579
- type: nauc_ndcg_at_1000_diff1
value: 79.98494037296896
- type: nauc_ndcg_at_1000_max
value: 72.09578054274171
- type: nauc_ndcg_at_1000_std
value: -2.480464992138408
- type: nauc_ndcg_at_100_diff1
value: 79.80423727797705
- type: nauc_ndcg_at_100_max
value: 72.0536867142539
- type: nauc_ndcg_at_100_std
value: -2.344303480460221
- type: nauc_ndcg_at_10_diff1
value: 79.4824234416871
- type: nauc_ndcg_at_10_max
value: 72.68066855765318
- type: nauc_ndcg_at_10_std
value: -1.0802283735752285
- type: nauc_ndcg_at_1_diff1
value: 83.07496179427446
- type: nauc_ndcg_at_1_max
value: 70.1472835630915
- type: nauc_ndcg_at_1_std
value: -4.892100745257178
- type: nauc_ndcg_at_20_diff1
value: 79.57286963155312
- type: nauc_ndcg_at_20_max
value: 72.45565146275474
- type: nauc_ndcg_at_20_std
value: -1.5388256709848513
- type: nauc_ndcg_at_3_diff1
value: 79.27965557528921
- type: nauc_ndcg_at_3_max
value: 73.21665805867235
- type: nauc_ndcg_at_3_std
value: -2.325102213384337
- type: nauc_ndcg_at_5_diff1
value: 79.24430450556383
- type: nauc_ndcg_at_5_max
value: 72.55798047361041
- type: nauc_ndcg_at_5_std
value: -1.346397266164686
- type: nauc_precision_at_1000_diff1
value: .nan
- type: nauc_precision_at_1000_max
value: .nan
- type: nauc_precision_at_1000_std
value: .nan
- type: nauc_precision_at_100_diff1
value: 48.65946378551628
- type: nauc_precision_at_100_max
value: 65.39282379618602
- type: nauc_precision_at_100_std
value: 24.616513271977254
- type: nauc_precision_at_10_diff1
value: 74.02416251053245
- type: nauc_precision_at_10_max
value: 77.2101523536241
- type: nauc_precision_at_10_std
value: 10.31518298376219
- type: nauc_precision_at_1_diff1
value: 83.07496179427446
- type: nauc_precision_at_1_max
value: 70.1472835630915
- type: nauc_precision_at_1_std
value: -4.892100745257178
- type: nauc_precision_at_20_diff1
value: 71.5107376283843
- type: nauc_precision_at_20_max
value: 77.21568627450955
- type: nauc_precision_at_20_std
value: 11.723622782445986
- type: nauc_precision_at_3_diff1
value: 75.76535137737912
- type: nauc_precision_at_3_max
value: 76.6685040168277
- type: nauc_precision_at_3_std
value: 1.5867736131175436
- type: nauc_precision_at_5_diff1
value: 74.58750059437934
- type: nauc_precision_at_5_max
value: 75.14502860946868
- type: nauc_precision_at_5_std
value: 5.935474156377063
- type: nauc_recall_at_1000_diff1
value: .nan
- type: nauc_recall_at_1000_max
value: .nan
- type: nauc_recall_at_1000_std
value: .nan
- type: nauc_recall_at_100_diff1
value: 48.6594637855143
- type: nauc_recall_at_100_max
value: 65.39282379618471
- type: nauc_recall_at_100_std
value: 24.616513271975943
- type: nauc_recall_at_10_diff1
value: 74.0241625105327
- type: nauc_recall_at_10_max
value: 77.21015235362442
- type: nauc_recall_at_10_std
value: 10.31518298376255
- type: nauc_recall_at_1_diff1
value: 83.07496179427446
- type: nauc_recall_at_1_max
value: 70.1472835630915
- type: nauc_recall_at_1_std
value: -4.892100745257178
- type: nauc_recall_at_20_diff1
value: 71.51073762838479
- type: nauc_recall_at_20_max
value: 77.21568627450962
- type: nauc_recall_at_20_std
value: 11.72362278244639
- type: nauc_recall_at_3_diff1
value: 75.7653513773791
- type: nauc_recall_at_3_max
value: 76.66850401682761
- type: nauc_recall_at_3_std
value: 1.5867736131174044
- type: nauc_recall_at_5_diff1
value: 74.58750059437952
- type: nauc_recall_at_5_max
value: 75.1450286094688
- type: nauc_recall_at_5_std
value: 5.935474156377355
- type: ndcg_at_1
value: 69.111
- type: ndcg_at_10
value: 80.204
- type: ndcg_at_100
value: 82.03399999999999
- type: ndcg_at_1000
value: 82.132
- type: ndcg_at_20
value: 81.119
- type: ndcg_at_3
value: 77.227
- type: ndcg_at_5
value: 78.781
- type: precision_at_1
value: 69.111
- type: precision_at_10
value: 9.089
- type: precision_at_100
value: 0.992
- type: precision_at_1000
value: 0.1
- type: precision_at_20
value: 4.7219999999999995
- type: precision_at_3
value: 27.556000000000004
- type: precision_at_5
value: 17.288999999999998
- type: recall_at_1
value: 69.111
- type: recall_at_10
value: 90.889
- type: recall_at_100
value: 99.222
- type: recall_at_1000
value: 100
- type: recall_at_20
value: 94.44399999999999
- type: recall_at_3
value: 82.667
- type: recall_at_5
value: 86.444
task:
type: Retrieval
- dataset:
config: hun_Latn-eng_Latn
name: MTEB BelebeleRetrieval (hun_Latn-eng_Latn)
revision: 75b399394a9803252cfec289d103de462763db7c
split: test
type: facebook/belebele
metrics:
- type: main_score
value: 75.395
- type: map_at_1
value: 62.666999999999994
- type: map_at_10
value: 71.30300000000001
- type: map_at_100
value: 71.774
- type: map_at_1000
value: 71.782
- type: map_at_20
value: 71.584
- type: map_at_3
value: 69.352
- type: map_at_5
value: 70.53
- type: mrr_at_1
value: 62.66666666666667
- type: mrr_at_10
value: 71.3027777777778
- type: mrr_at_100
value: 71.77425164712943
- type: mrr_at_1000
value: 71.78156792911966
- type: mrr_at_20
value: 71.58381913064578
- type: mrr_at_3
value: 69.35185185185185
- type: mrr_at_5
value: 70.52962962962965
- type: nauc_map_at_1000_diff1
value: 75.881602960504
- type: nauc_map_at_1000_max
value: 68.66296274339753
- type: nauc_map_at_1000_std
value: 7.517075184571474
- type: nauc_map_at_100_diff1
value: 75.8786843747508
- type: nauc_map_at_100_max
value: 68.66828124033619
- type: nauc_map_at_100_std
value: 7.525587871036576
- type: nauc_map_at_10_diff1
value: 75.5973833371205
- type: nauc_map_at_10_max
value: 68.65021557056664
- type: nauc_map_at_10_std
value: 7.562660323790659
- type: nauc_map_at_1_diff1
value: 79.25984371863814
- type: nauc_map_at_1_max
value: 66.56457853173036
- type: nauc_map_at_1_std
value: 3.9501186990857162
- type: nauc_map_at_20_diff1
value: 75.85810159356491
- type: nauc_map_at_20_max
value: 68.76976086961005
- type: nauc_map_at_20_std
value: 7.819971956110064
- type: nauc_map_at_3_diff1
value: 75.89565847594535
- type: nauc_map_at_3_max
value: 68.86426509148927
- type: nauc_map_at_3_std
value: 6.916006381683043
- type: nauc_map_at_5_diff1
value: 75.61832788795184
- type: nauc_map_at_5_max
value: 68.66734871116772
- type: nauc_map_at_5_std
value: 7.108445006055354
- type: nauc_mrr_at_1000_diff1
value: 75.881602960504
- type: nauc_mrr_at_1000_max
value: 68.66296274339753
- type: nauc_mrr_at_1000_std
value: 7.517075184571474
- type: nauc_mrr_at_100_diff1
value: 75.8786843747508
- type: nauc_mrr_at_100_max
value: 68.66828124033619
- type: nauc_mrr_at_100_std
value: 7.525587871036576
- type: nauc_mrr_at_10_diff1
value: 75.5973833371205
- type: nauc_mrr_at_10_max
value: 68.65021557056664
- type: nauc_mrr_at_10_std
value: 7.562660323790659
- type: nauc_mrr_at_1_diff1
value: 79.25984371863814
- type: nauc_mrr_at_1_max
value: 66.56457853173036
- type: nauc_mrr_at_1_std
value: 3.9501186990857162
- type: nauc_mrr_at_20_diff1
value: 75.85810159356491
- type: nauc_mrr_at_20_max
value: 68.76976086961005
- type: nauc_mrr_at_20_std
value: 7.819971956110064
- type: nauc_mrr_at_3_diff1
value: 75.89565847594535
- type: nauc_mrr_at_3_max
value: 68.86426509148927
- type: nauc_mrr_at_3_std
value: 6.916006381683043
- type: nauc_mrr_at_5_diff1
value: 75.61832788795184
- type: nauc_mrr_at_5_max
value: 68.66734871116772
- type: nauc_mrr_at_5_std
value: 7.108445006055354
- type: nauc_ndcg_at_1000_diff1
value: 75.2994418691362
- type: nauc_ndcg_at_1000_max
value: 69.06426768849241
- type: nauc_ndcg_at_1000_std
value: 8.535785357759078
- type: nauc_ndcg_at_100_diff1
value: 75.24120510322648
- type: nauc_ndcg_at_100_max
value: 69.20598137031494
- type: nauc_ndcg_at_100_std
value: 8.809082971368174
- type: nauc_ndcg_at_10_diff1
value: 73.85929786184265
- type: nauc_ndcg_at_10_max
value: 69.35906735202224
- type: nauc_ndcg_at_10_std
value: 9.803390649271314
- type: nauc_ndcg_at_1_diff1
value: 79.25984371863814
- type: nauc_ndcg_at_1_max
value: 66.56457853173036
- type: nauc_ndcg_at_1_std
value: 3.9501186990857162
- type: nauc_ndcg_at_20_diff1
value: 74.908346673254
- type: nauc_ndcg_at_20_max
value: 69.94089128246969
- type: nauc_ndcg_at_20_std
value: 11.040261082698441
- type: nauc_ndcg_at_3_diff1
value: 74.63723173221176
- type: nauc_ndcg_at_3_max
value: 69.66882097579499
- type: nauc_ndcg_at_3_std
value: 8.070938288986905
- type: nauc_ndcg_at_5_diff1
value: 74.03823148610475
- type: nauc_ndcg_at_5_max
value: 69.35847081273427
- type: nauc_ndcg_at_5_std
value: 8.544629619697409
- type: nauc_precision_at_1000_diff1
value: .nan
- type: nauc_precision_at_1000_max
value: .nan
- type: nauc_precision_at_1000_std
value: .nan
- type: nauc_precision_at_100_diff1
value: 68.52007469654558
- type: nauc_precision_at_100_max
value: 86.99813258636793
- type: nauc_precision_at_100_std
value: 44.83193277310911
- type: nauc_precision_at_10_diff1
value: 63.121147314127334
- type: nauc_precision_at_10_max
value: 73.48453534137256
- type: nauc_precision_at_10_std
value: 24.29146523372198
- type: nauc_precision_at_1_diff1
value: 79.25984371863814
- type: nauc_precision_at_1_max
value: 66.56457853173036
- type: nauc_precision_at_1_std
value: 3.9501186990857162
- type: nauc_precision_at_20_diff1
value: 68.71215152727741
- type: nauc_precision_at_20_max
value: 81.60730959050274
- type: nauc_precision_at_20_std
value: 44.10897692410284
- type: nauc_precision_at_3_diff1
value: 70.11884635511014
- type: nauc_precision_at_3_max
value: 72.53602624481753
- type: nauc_precision_at_3_std
value: 12.235337922151093
- type: nauc_precision_at_5_diff1
value: 67.13640746909785
- type: nauc_precision_at_5_max
value: 72.25763628849465
- type: nauc_precision_at_5_std
value: 14.868376560758348
- type: nauc_recall_at_1000_diff1
value: .nan
- type: nauc_recall_at_1000_max
value: .nan
- type: nauc_recall_at_1000_std
value: .nan
- type: nauc_recall_at_100_diff1
value: 68.52007469654454
- type: nauc_recall_at_100_max
value: 86.99813258636755
- type: nauc_recall_at_100_std
value: 44.83193277310874
- type: nauc_recall_at_10_diff1
value: 63.121147314127604
- type: nauc_recall_at_10_max
value: 73.48453534137263
- type: nauc_recall_at_10_std
value: 24.291465233722057
- type: nauc_recall_at_1_diff1
value: 79.25984371863814
- type: nauc_recall_at_1_max
value: 66.56457853173036
- type: nauc_recall_at_1_std
value: 3.9501186990857162
- type: nauc_recall_at_20_diff1
value: 68.71215152727751
- type: nauc_recall_at_20_max
value: 81.60730959050267
- type: nauc_recall_at_20_std
value: 44.10897692410295
- type: nauc_recall_at_3_diff1
value: 70.11884635511011
- type: nauc_recall_at_3_max
value: 72.5360262448175
- type: nauc_recall_at_3_std
value: 12.23533792215117
- type: nauc_recall_at_5_diff1
value: 67.13640746909788
- type: nauc_recall_at_5_max
value: 72.25763628849458
- type: nauc_recall_at_5_std
value: 14.868376560758476
- type: ndcg_at_1
value: 62.666999999999994
- type: ndcg_at_10
value: 75.395
- type: ndcg_at_100
value: 77.684
- type: ndcg_at_1000
value: 77.836
- type: ndcg_at_20
value: 76.41
- type: ndcg_at_3
value: 71.411
- type: ndcg_at_5
value: 73.52499999999999
- type: precision_at_1
value: 62.666999999999994
- type: precision_at_10
value: 8.822000000000001
- type: precision_at_100
value: 0.989
- type: precision_at_1000
value: 0.1
- type: precision_at_20
value: 4.611
- type: precision_at_3
value: 25.778000000000002
- type: precision_at_5
value: 16.489
- type: recall_at_1
value: 62.666999999999994
- type: recall_at_10
value: 88.222
- type: recall_at_100
value: 98.88900000000001
- type: recall_at_1000
value: 100
- type: recall_at_20
value: 92.22200000000001
- type: recall_at_3
value: 77.333
- type: recall_at_5
value: 82.44399999999999
task:
type: Retrieval
- dataset:
config: eng_Latn-hun_Latn
name: MTEB BelebeleRetrieval (eng_Latn-hun_Latn)
revision: 75b399394a9803252cfec289d103de462763db7c
split: test
type: facebook/belebele
metrics:
- type: main_score
value: 76.872
- type: map_at_1
value: 65
- type: map_at_10
value: 72.896
- type: map_at_100
value: 73.358
- type: map_at_1000
value: 73.36500000000001
- type: map_at_20
value: 73.2
- type: map_at_3
value: 70.907
- type: map_at_5
value: 72.002
- type: mrr_at_1
value: 65
- type: mrr_at_10
value: 72.89603174603175
- type: mrr_at_100
value: 73.3579205518051
- type: mrr_at_1000
value: 73.3654112460061
- type: mrr_at_20
value: 73.19952956877624
- type: mrr_at_3
value: 70.90740740740742
- type: mrr_at_5
value: 72.00185185185185
- type: nauc_map_at_1000_diff1
value: 77.77369357560062
- type: nauc_map_at_1000_max
value: 70.94830494912476
- type: nauc_map_at_1000_std
value: 6.522974403262641
- type: nauc_map_at_100_diff1
value: 77.77362905601957
- type: nauc_map_at_100_max
value: 70.95095989526841
- type: nauc_map_at_100_std
value: 6.5352551972569435
- type: nauc_map_at_10_diff1
value: 77.5247904322094
- type: nauc_map_at_10_max
value: 71.02603340796348
- type: nauc_map_at_10_std
value: 6.757278192437519
- type: nauc_map_at_1_diff1
value: 80.6553286136653
- type: nauc_map_at_1_max
value: 68.35724812614716
- type: nauc_map_at_1_std
value: 4.038661494923131
- type: nauc_map_at_20_diff1
value: 77.68304529150893
- type: nauc_map_at_20_max
value: 70.95365196926124
- type: nauc_map_at_20_std
value: 6.459235608230074
- type: nauc_map_at_3_diff1
value: 77.65108311925263
- type: nauc_map_at_3_max
value: 71.27300229679268
- type: nauc_map_at_3_std
value: 6.421413249698873
- type: nauc_map_at_5_diff1
value: 77.62058612073584
- type: nauc_map_at_5_max
value: 71.28166308466814
- type: nauc_map_at_5_std
value: 7.148832281239676
- type: nauc_mrr_at_1000_diff1
value: 77.77369357560062
- type: nauc_mrr_at_1000_max
value: 70.94830494912476
- type: nauc_mrr_at_1000_std
value: 6.522974403262641
- type: nauc_mrr_at_100_diff1
value: 77.77362905601957
- type: nauc_mrr_at_100_max
value: 70.95095989526841
- type: nauc_mrr_at_100_std
value: 6.5352551972569435
- type: nauc_mrr_at_10_diff1
value: 77.5247904322094
- type: nauc_mrr_at_10_max
value: 71.02603340796348
- type: nauc_mrr_at_10_std
value: 6.757278192437519
- type: nauc_mrr_at_1_diff1
value: 80.6553286136653
- type: nauc_mrr_at_1_max
value: 68.35724812614716
- type: nauc_mrr_at_1_std
value: 4.038661494923131
- type: nauc_mrr_at_20_diff1
value: 77.68304529150893
- type: nauc_mrr_at_20_max
value: 70.95365196926124
- type: nauc_mrr_at_20_std
value: 6.459235608230074
- type: nauc_mrr_at_3_diff1
value: 77.65108311925263
- type: nauc_mrr_at_3_max
value: 71.27300229679268
- type: nauc_mrr_at_3_std
value: 6.421413249698873
- type: nauc_mrr_at_5_diff1
value: 77.62058612073584
- type: nauc_mrr_at_5_max
value: 71.28166308466814
- type: nauc_mrr_at_5_std
value: 7.148832281239676
- type: nauc_ndcg_at_1000_diff1
value: 77.32834118213609
- type: nauc_ndcg_at_1000_max
value: 71.28407034639005
- type: nauc_ndcg_at_1000_std
value: 7.054791737753761
- type: nauc_ndcg_at_100_diff1
value: 77.3138740535263
- type: nauc_ndcg_at_100_max
value: 71.38841430408482
- type: nauc_ndcg_at_100_std
value: 7.495181794448738
- type: nauc_ndcg_at_10_diff1
value: 76.09808428652988
- type: nauc_ndcg_at_10_max
value: 71.69225339870586
- type: nauc_ndcg_at_10_std
value: 8.049899262534995
- type: nauc_ndcg_at_1_diff1
value: 80.6553286136653
- type: nauc_ndcg_at_1_max
value: 68.35724812614716
- type: nauc_ndcg_at_1_std
value: 4.038661494923131
- type: nauc_ndcg_at_20_diff1
value: 76.72021561109376
- type: nauc_ndcg_at_20_max
value: 71.44696555289187
- type: nauc_ndcg_at_20_std
value: 6.921724399287313
- type: nauc_ndcg_at_3_diff1
value: 76.56243231944167
- type: nauc_ndcg_at_3_max
value: 72.19254115417164
- type: nauc_ndcg_at_3_std
value: 7.41142651827797
- type: nauc_ndcg_at_5_diff1
value: 76.42995455832103
- type: nauc_ndcg_at_5_max
value: 72.29448332833202
- type: nauc_ndcg_at_5_std
value: 8.945757639249557
- type: nauc_precision_at_1000_diff1
value: .nan
- type: nauc_precision_at_1000_max
value: .nan
- type: nauc_precision_at_1000_std
value: .nan
- type: nauc_precision_at_100_diff1
value: 75.5835667600378
- type: nauc_precision_at_100_max
value: 81.91840838899772
- type: nauc_precision_at_100_std
value: 50.65000359118282
- type: nauc_precision_at_10_diff1
value: 66.80290959473481
- type: nauc_precision_at_10_max
value: 75.3540501756643
- type: nauc_precision_at_10_std
value: 16.157652531050392
- type: nauc_precision_at_1_diff1
value: 80.6553286136653
- type: nauc_precision_at_1_max
value: 68.35724812614716
- type: nauc_precision_at_1_std
value: 4.038661494923131
- type: nauc_precision_at_20_diff1
value: 68.47710835746726
- type: nauc_precision_at_20_max
value: 74.90069474117318
- type: nauc_precision_at_20_std
value: 8.589311430786644
- type: nauc_precision_at_3_diff1
value: 72.69790694125835
- type: nauc_precision_at_3_max
value: 75.40287436733661
- type: nauc_precision_at_3_std
value: 10.97556244649672
- type: nauc_precision_at_5_diff1
value: 71.35323836023953
- type: nauc_precision_at_5_max
value: 76.56660725505522
- type: nauc_precision_at_5_std
value: 17.011489094336106
- type: nauc_recall_at_1000_diff1
value: .nan
- type: nauc_recall_at_1000_max
value: .nan
- type: nauc_recall_at_1000_std
value: .nan
- type: nauc_recall_at_100_diff1
value: 75.58356676003798
- type: nauc_recall_at_100_max
value: 81.9184083889972
- type: nauc_recall_at_100_std
value: 50.65000359118012
- type: nauc_recall_at_10_diff1
value: 66.80290959473508
- type: nauc_recall_at_10_max
value: 75.35405017566428
- type: nauc_recall_at_10_std
value: 16.157652531050555
- type: nauc_recall_at_1_diff1
value: 80.6553286136653
- type: nauc_recall_at_1_max
value: 68.35724812614716
- type: nauc_recall_at_1_std
value: 4.038661494923131
- type: nauc_recall_at_20_diff1
value: 68.47710835746722
- type: nauc_recall_at_20_max
value: 74.90069474117321
- type: nauc_recall_at_20_std
value: 8.589311430787212
- type: nauc_recall_at_3_diff1
value: 72.69790694125835
- type: nauc_recall_at_3_max
value: 75.40287436733665
- type: nauc_recall_at_3_std
value: 10.97556244649683
- type: nauc_recall_at_5_diff1
value: 71.35323836023952
- type: nauc_recall_at_5_max
value: 76.56660725505535
- type: nauc_recall_at_5_std
value: 17.011489094336287
- type: ndcg_at_1
value: 65
- type: ndcg_at_10
value: 76.872
- type: ndcg_at_100
value: 78.914
- type: ndcg_at_1000
value: 79.103
- type: ndcg_at_20
value: 77.916
- type: ndcg_at_3
value: 72.763
- type: ndcg_at_5
value: 74.733
- type: precision_at_1
value: 65
- type: precision_at_10
value: 8.944
- type: precision_at_100
value: 0.9860000000000001
- type: precision_at_1000
value: 0.1
- type: precision_at_20
value: 4.672
- type: precision_at_3
value: 26.037
- type: precision_at_5
value: 16.578
- type: recall_at_1
value: 65
- type: recall_at_10
value: 89.444
- type: recall_at_100
value: 98.556
- type: recall_at_1000
value: 100
- type: recall_at_20
value: 93.444
- type: recall_at_3
value: 78.11099999999999
- type: recall_at_5
value: 82.889
task:
type: Retrieval
- dataset:
config: eng_Latn-hun_Latn
name: MTEB BibleNLPBitextMining (eng_Latn-hun_Latn)
revision: 264a18480c529d9e922483839b4b9758e690b762
split: train
type: davidstap/biblenlp-corpus-mmteb
metrics:
- type: accuracy
value: 90.234375
- type: f1
value: 87.39583333333334
- type: main_score
value: 87.39583333333334
- type: precision
value: 86.16536458333334
- type: recall
value: 90.234375
task:
type: BitextMining
- dataset:
config: hun_Latn-eng_Latn
name: MTEB BibleNLPBitextMining (hun_Latn-eng_Latn)
revision: 264a18480c529d9e922483839b4b9758e690b762
split: train
type: davidstap/biblenlp-corpus-mmteb
metrics:
- type: accuracy
value: 94.140625
- type: f1
value: 92.31770833333333
- type: main_score
value: 92.31770833333333
- type: precision
value: 91.47135416666667
- type: recall
value: 94.140625
task:
type: BitextMining
- dataset:
config: default
name: MTEB HunSum2AbstractiveRetrieval (default)
revision: 24e1445c8180d937f0a16f8ae8a62e77cc952e56
split: test
type: SZTAKI-HLT/HunSum-2-abstractive
metrics:
- type: main_score
value: 65.616
- type: map_at_1
value: 65.616
- type: map_at_10
value: 72.17
- type: map_at_100
value: 72.596
- type: map_at_1000
value: 72.615
- type: map_at_20
value: 72.418
- type: map_at_3
value: 70.596
- type: map_at_5
value: 71.532
- type: mrr_at_1
value: 65.61561561561562
- type: mrr_at_10
value: 72.17006689228913
- type: mrr_at_100
value: 72.59630726413003
- type: mrr_at_1000
value: 72.61533408042457
- type: mrr_at_20
value: 72.41848803381308
- type: mrr_at_3
value: 70.59559559559558
- type: mrr_at_5
value: 71.53153153153156
- type: nauc_map_at_1000_diff1
value: 82.11477551036097
- type: nauc_map_at_1000_max
value: 69.93216235961877
- type: nauc_map_at_1000_std
value: -4.901120373521347
- type: nauc_map_at_100_diff1
value: 82.10806987112343
- type: nauc_map_at_100_max
value: 69.93576246377116
- type: nauc_map_at_100_std
value: -4.888276482937281
- type: nauc_map_at_10_diff1
value: 82.04302562091283
- type: nauc_map_at_10_max
value: 69.98073646418275
- type: nauc_map_at_10_std
value: -4.939406021960221
- type: nauc_map_at_1_diff1
value: 85.20668775288361
- type: nauc_map_at_1_max
value: 69.09789335497814
- type: nauc_map_at_1_std
value: -6.442884331049151
- type: nauc_map_at_20_diff1
value: 82.0225558509114
- type: nauc_map_at_20_max
value: 69.91856798991726
- type: nauc_map_at_20_std
value: -4.865775113195285
- type: nauc_map_at_3_diff1
value: 82.27637852190405
- type: nauc_map_at_3_max
value: 70.15220150711396
- type: nauc_map_at_3_std
value: -5.459983423558685
- type: nauc_map_at_5_diff1
value: 81.99868387570363
- type: nauc_map_at_5_max
value: 69.96808732325626
- type: nauc_map_at_5_std
value: -5.066978528413986
- type: nauc_mrr_at_1000_diff1
value: 82.11477551036097
- type: nauc_mrr_at_1000_max
value: 69.93216235961877
- type: nauc_mrr_at_1000_std
value: -4.901120373521347
- type: nauc_mrr_at_100_diff1
value: 82.10806987112343
- type: nauc_mrr_at_100_max
value: 69.93576246377116
- type: nauc_mrr_at_100_std
value: -4.888276482937281
- type: nauc_mrr_at_10_diff1
value: 82.04302562091283
- type: nauc_mrr_at_10_max
value: 69.98073646418275
- type: nauc_mrr_at_10_std
value: -4.939406021960221
- type: nauc_mrr_at_1_diff1
value: 85.20668775288361
- type: nauc_mrr_at_1_max
value: 69.09789335497814
- type: nauc_mrr_at_1_std
value: -6.442884331049151
- type: nauc_mrr_at_20_diff1
value: 82.0225558509114
- type: nauc_mrr_at_20_max
value: 69.91856798991726
- type: nauc_mrr_at_20_std
value: -4.865775113195285
- type: nauc_mrr_at_3_diff1
value: 82.27637852190405
- type: nauc_mrr_at_3_max
value: 70.15220150711396
- type: nauc_mrr_at_3_std
value: -5.459983423558685
- type: nauc_mrr_at_5_diff1
value: 81.99868387570363
- type: nauc_mrr_at_5_max
value: 69.96808732325626
- type: nauc_mrr_at_5_std
value: -5.066978528413986
- type: nauc_ndcg_at_1000_diff1
value: 81.5126840771622
- type: nauc_ndcg_at_1000_max
value: 70.12763018849093
- type: nauc_ndcg_at_1000_std
value: -3.990763331803255
- type: nauc_ndcg_at_100_diff1
value: 81.35314690542201
- type: nauc_ndcg_at_100_max
value: 70.29954500310211
- type: nauc_ndcg_at_100_std
value: -3.4200000144945704
- type: nauc_ndcg_at_10_diff1
value: 80.79088866851619
- type: nauc_ndcg_at_10_max
value: 70.32243683355195
- type: nauc_ndcg_at_10_std
value: -3.661632655363061
- type: nauc_ndcg_at_1_diff1
value: 85.20668775288361
- type: nauc_ndcg_at_1_max
value: 69.09789335497814
- type: nauc_ndcg_at_1_std
value: -6.442884331049151
- type: nauc_ndcg_at_20_diff1
value: 80.65723696292129
- type: nauc_ndcg_at_20_max
value: 70.0781627958487
- type: nauc_ndcg_at_20_std
value: -3.3268850467427455
- type: nauc_ndcg_at_3_diff1
value: 81.30422620216359
- type: nauc_ndcg_at_3_max
value: 70.57201377939089
- type: nauc_ndcg_at_3_std
value: -4.867226820935226
- type: nauc_ndcg_at_5_diff1
value: 80.73570523236309
- type: nauc_ndcg_at_5_max
value: 70.26219056465638
- type: nauc_ndcg_at_5_std
value: -4.058787558085215
- type: nauc_precision_at_1000_diff1
value: 74.43924751465183
- type: nauc_precision_at_1000_max
value: 86.51759703882918
- type: nauc_precision_at_1000_std
value: 82.31711770484912
- type: nauc_precision_at_100_diff1
value: 75.70004441716591
- type: nauc_precision_at_100_max
value: 77.61085332471666
- type: nauc_precision_at_100_std
value: 22.502459762868824
- type: nauc_precision_at_10_diff1
value: 74.62622879461453
- type: nauc_precision_at_10_max
value: 72.02341591543264
- type: nauc_precision_at_10_std
value: 3.227096017453475
- type: nauc_precision_at_1_diff1
value: 85.20668775288361
- type: nauc_precision_at_1_max
value: 69.09789335497814
- type: nauc_precision_at_1_std
value: -6.442884331049151
- type: nauc_precision_at_20_diff1
value: 71.82812396378273
- type: nauc_precision_at_20_max
value: 70.67250776468195
- type: nauc_precision_at_20_std
value: 7.67961919934869
- type: nauc_precision_at_3_diff1
value: 78.00819461913801
- type: nauc_precision_at_3_max
value: 72.02361600228878
- type: nauc_precision_at_3_std
value: -2.749950579759329
- type: nauc_precision_at_5_diff1
value: 75.76784513448565
- type: nauc_precision_at_5_max
value: 71.38070257500367
- type: nauc_precision_at_5_std
value: 0.14048678160511355
- type: nauc_recall_at_1000_diff1
value: 74.43924751465049
- type: nauc_recall_at_1000_max
value: 86.51759703883047
- type: nauc_recall_at_1000_std
value: 82.31711770484824
- type: nauc_recall_at_100_diff1
value: 75.70004441716617
- type: nauc_recall_at_100_max
value: 77.61085332471673
- type: nauc_recall_at_100_std
value: 22.502459762868686
- type: nauc_recall_at_10_diff1
value: 74.62622879461455
- type: nauc_recall_at_10_max
value: 72.02341591543261
- type: nauc_recall_at_10_std
value: 3.2270960174534973
- type: nauc_recall_at_1_diff1
value: 85.20668775288361
- type: nauc_recall_at_1_max
value: 69.09789335497814
- type: nauc_recall_at_1_std
value: -6.442884331049151
- type: nauc_recall_at_20_diff1
value: 71.82812396378263
- type: nauc_recall_at_20_max
value: 70.6725077646819
- type: nauc_recall_at_20_std
value: 7.679619199348971
- type: nauc_recall_at_3_diff1
value: 78.00819461913807
- type: nauc_recall_at_3_max
value: 72.02361600228886
- type: nauc_recall_at_3_std
value: -2.749950579759317
- type: nauc_recall_at_5_diff1
value: 75.76784513448574
- type: nauc_recall_at_5_max
value: 71.38070257500377
- type: nauc_recall_at_5_std
value: 0.1404867816050954
- type: ndcg_at_1
value: 65.616
- type: ndcg_at_10
value: 75.372
- type: ndcg_at_100
value: 77.536
- type: ndcg_at_1000
value: 78.051
- type: ndcg_at_20
value: 76.281
- type: ndcg_at_3
value: 72.162
- type: ndcg_at_5
value: 73.83999999999999
- type: precision_at_1
value: 65.616
- type: precision_at_10
value: 8.544
- type: precision_at_100
value: 0.9570000000000001
- type: precision_at_1000
value: 0.1
- type: precision_at_20
value: 4.452
- type: precision_at_3
value: 25.558999999999997
- type: precision_at_5
value: 16.146
- type: recall_at_1
value: 65.616
- type: recall_at_10
value: 85.435
- type: recall_at_100
value: 95.746
- type: recall_at_1000
value: 99.8
- type: recall_at_20
value: 89.039
- type: recall_at_3
value: 76.67699999999999
- type: recall_at_5
value: 80.731
task:
type: Retrieval
- dataset:
config: hu
name: MTEB MassiveIntentClassification (hu)
revision: 4672e20407010da34463acc759c162ca9734bca6
split: test
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 61.93678547410896
- type: f1
value: 59.18089758951288
- type: f1_weighted
value: 62.33480431880768
- type: main_score
value: 61.93678547410896
task:
type: Classification
- dataset:
config: hu
name: MTEB MassiveIntentClassification (hu)
revision: 4672e20407010da34463acc759c162ca9734bca6
split: validation
type: mteb/amazon_massive_intent
metrics:
- type: accuracy
value: 61.65272995573046
- type: f1
value: 59.300294731108615
- type: f1_weighted
value: 61.95329485924452
- type: main_score
value: 61.65272995573046
task:
type: Classification
- dataset:
config: hu
name: MTEB MassiveScenarioClassification (hu)
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
split: test
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 66.93342299932749
- type: f1
value: 66.09393745126239
- type: f1_weighted
value: 67.11013732647363
- type: main_score
value: 66.93342299932749
task:
type: Classification
- dataset:
config: hu
name: MTEB MassiveScenarioClassification (hu)
revision: fad2c6e8459f9e1c45d9315f4953d921437d70f8
split: validation
type: mteb/amazon_massive_scenario
metrics:
- type: accuracy
value: 66.27643876045252
- type: f1
value: 65.84263838771432
- type: f1_weighted
value: 66.48633782928637
- type: main_score
value: 66.27643876045252
task:
type: Classification
- dataset:
config: hu
name: MTEB MultiEURLEXMultilabelClassification (hu)
revision: 2aea5a6dc8fdcfeca41d0fb963c0a338930bde5c
split: test
type: mteb/eurlex-multilingual
metrics:
- type: accuracy
value: 2.6879999999999997
- type: f1
value: 25.112198433514166
- type: lrap
value: 41.790686190475135
- type: main_score
value: 2.6879999999999997
task:
type: MultilabelClassification
- dataset:
config: arb_Arab-hun_Latn
name: MTEB NTREXBitextMining (arb_Arab-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 86.07911867801702
- type: f1
value: 82.34184610248707
- type: main_score
value: 82.34184610248707
- type: precision
value: 80.65598397596395
- type: recall
value: 86.07911867801702
task:
type: BitextMining
- dataset:
config: ben_Beng-hun_Latn
name: MTEB NTREXBitextMining (ben_Beng-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 40.91136705057586
- type: f1
value: 36.01175728956383
- type: main_score
value: 36.01175728956383
- type: precision
value: 34.36916434339978
- type: recall
value: 40.91136705057586
task:
type: BitextMining
- dataset:
config: deu_Latn-hun_Latn
name: MTEB NTREXBitextMining (deu_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.54031046569855
- type: f1
value: 91.73760640961443
- type: main_score
value: 91.73760640961443
- type: precision
value: 90.87130696044066
- type: recall
value: 93.54031046569855
task:
type: BitextMining
- dataset:
config: ell_Grek-hun_Latn
name: MTEB NTREXBitextMining (ell_Grek-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.3870806209314
- type: f1
value: 88.87998664663662
- type: main_score
value: 88.87998664663662
- type: precision
value: 87.69821398764815
- type: recall
value: 91.3870806209314
task:
type: BitextMining
- dataset:
config: eng_Latn-hun_Latn
name: MTEB NTREXBitextMining (eng_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 94.69203805708563
- type: f1
value: 93.04790519112001
- type: main_score
value: 93.04790519112001
- type: precision
value: 92.24670338841595
- type: recall
value: 94.69203805708563
task:
type: BitextMining
- dataset:
config: fas_Arab-hun_Latn
name: MTEB NTREXBitextMining (fas_Arab-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 89.43415122684027
- type: f1
value: 86.48138874979135
- type: main_score
value: 86.48138874979135
- type: precision
value: 85.1235186112502
- type: recall
value: 89.43415122684027
task:
type: BitextMining
- dataset:
config: fin_Latn-hun_Latn
name: MTEB NTREXBitextMining (fin_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.73610415623435
- type: f1
value: 88.10716074111167
- type: main_score
value: 88.10716074111167
- type: precision
value: 86.84860624269739
- type: recall
value: 90.73610415623435
task:
type: BitextMining
- dataset:
config: fra_Latn-hun_Latn
name: MTEB NTREXBitextMining (fra_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.03955933900852
- type: f1
value: 90.97312635620098
- type: main_score
value: 90.97312635620098
- type: precision
value: 89.97245868803205
- type: recall
value: 93.03955933900852
task:
type: BitextMining
- dataset:
config: heb_Hebr-hun_Latn
name: MTEB NTREXBitextMining (heb_Hebr-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 88.03204807210815
- type: f1
value: 84.71540644299783
- type: main_score
value: 84.71540644299783
- type: precision
value: 83.14972458688032
- type: recall
value: 88.03204807210815
task:
type: BitextMining
- dataset:
config: hin_Deva-hun_Latn
name: MTEB NTREXBitextMining (hin_Deva-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 86.9804707060591
- type: f1
value: 83.51527290936404
- type: main_score
value: 83.51527290936404
- type: precision
value: 81.92038057085628
- type: recall
value: 86.9804707060591
task:
type: BitextMining
- dataset:
config: hun_Latn-arb_Arab
name: MTEB NTREXBitextMining (hun_Latn-arb_Arab)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 86.47971957936905
- type: f1
value: 82.83592054748789
- type: main_score
value: 82.83592054748789
- type: precision
value: 81.18260724419963
- type: recall
value: 86.47971957936905
task:
type: BitextMining
- dataset:
config: hun_Latn-ben_Beng
name: MTEB NTREXBitextMining (hun_Latn-ben_Beng)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 41.86279419128693
- type: f1
value: 33.232896964494365
- type: main_score
value: 33.232896964494365
- type: precision
value: 30.249043850094402
- type: recall
value: 41.86279419128693
task:
type: BitextMining
- dataset:
config: hun_Latn-deu_Latn
name: MTEB NTREXBitextMining (hun_Latn-deu_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.94091136705057
- type: f1
value: 92.14989150392255
- type: main_score
value: 92.14989150392255
- type: precision
value: 91.28275746953764
- type: recall
value: 93.94091136705057
task:
type: BitextMining
- dataset:
config: hun_Latn-ell_Grek
name: MTEB NTREXBitextMining (hun_Latn-ell_Grek)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.8392588883325
- type: f1
value: 90.86296110832916
- type: main_score
value: 90.86296110832916
- type: precision
value: 89.93072942747456
- type: recall
value: 92.8392588883325
task:
type: BitextMining
- dataset:
config: hun_Latn-eng_Latn
name: MTEB NTREXBitextMining (hun_Latn-eng_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 95.54331497245869
- type: f1
value: 94.2330161909531
- type: main_score
value: 94.2330161909531
- type: precision
value: 93.59873143047905
- type: recall
value: 95.54331497245869
task:
type: BitextMining
- dataset:
config: hun_Latn-fas_Arab
name: MTEB NTREXBitextMining (hun_Latn-fas_Arab)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 89.43415122684027
- type: f1
value: 86.54481722583876
- type: main_score
value: 86.54481722583876
- type: precision
value: 85.20447337673176
- type: recall
value: 89.43415122684027
task:
type: BitextMining
- dataset:
config: hun_Latn-fin_Latn
name: MTEB NTREXBitextMining (hun_Latn-fin_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 89.58437656484726
- type: f1
value: 86.70839592722417
- type: main_score
value: 86.70839592722417
- type: precision
value: 85.37389417459522
- type: recall
value: 89.58437656484726
task:
type: BitextMining
- dataset:
config: hun_Latn-fra_Latn
name: MTEB NTREXBitextMining (hun_Latn-fra_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.13820731096645
- type: f1
value: 89.883158070439
- type: main_score
value: 89.883158070439
- type: precision
value: 88.81822734101151
- type: recall
value: 92.13820731096645
task:
type: BitextMining
- dataset:
config: hun_Latn-heb_Hebr
name: MTEB NTREXBitextMining (hun_Latn-heb_Hebr)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 86.93039559339009
- type: f1
value: 83.32336166587544
- type: main_score
value: 83.32336166587544
- type: precision
value: 81.67334334835587
- type: recall
value: 86.93039559339009
task:
type: BitextMining
- dataset:
config: hun_Latn-hin_Deva
name: MTEB NTREXBitextMining (hun_Latn-hin_Deva)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 85.97896845267901
- type: f1
value: 82.34685361375396
- type: main_score
value: 82.34685361375396
- type: precision
value: 80.72859288933401
- type: recall
value: 85.97896845267901
task:
type: BitextMining
- dataset:
config: hun_Latn-ind_Latn
name: MTEB NTREXBitextMining (hun_Latn-ind_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.33850776164246
- type: f1
value: 90.06843598731432
- type: main_score
value: 90.06843598731432
- type: precision
value: 88.97512936070773
- type: recall
value: 92.33850776164246
task:
type: BitextMining
- dataset:
config: hun_Latn-jpn_Jpan
name: MTEB NTREXBitextMining (hun_Latn-jpn_Jpan)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 87.48122183274913
- type: f1
value: 84.08779836421299
- type: main_score
value: 84.08779836421299
- type: precision
value: 82.53380070105159
- type: recall
value: 87.48122183274913
task:
type: BitextMining
- dataset:
config: hun_Latn-kor_Hang
name: MTEB NTREXBitextMining (hun_Latn-kor_Hang)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 84.82724086129194
- type: f1
value: 80.77859213062017
- type: main_score
value: 80.77859213062017
- type: precision
value: 78.98931730929726
- type: recall
value: 84.82724086129194
task:
type: BitextMining
- dataset:
config: hun_Latn-lav_Latn
name: MTEB NTREXBitextMining (hun_Latn-lav_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 89.9849774661993
- type: f1
value: 87.0422300116842
- type: main_score
value: 87.0422300116842
- type: precision
value: 85.65932231680856
- type: recall
value: 89.9849774661993
task:
type: BitextMining
- dataset:
config: hun_Latn-lit_Latn
name: MTEB NTREXBitextMining (hun_Latn-lit_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.38557836755132
- type: f1
value: 87.60474044399933
- type: main_score
value: 87.60474044399933
- type: precision
value: 86.28776498080455
- type: recall
value: 90.38557836755132
task:
type: BitextMining
- dataset:
config: hun_Latn-nld_Latn
name: MTEB NTREXBitextMining (hun_Latn-nld_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.64046069103655
- type: f1
value: 91.81271907861792
- type: main_score
value: 91.81271907861792
- type: precision
value: 90.93807377733266
- type: recall
value: 93.64046069103655
task:
type: BitextMining
- dataset:
config: hun_Latn-pol_Latn
name: MTEB NTREXBitextMining (hun_Latn-pol_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.2368552829244
- type: f1
value: 88.85924124281661
- type: main_score
value: 88.85924124281661
- type: precision
value: 87.7524620263729
- type: recall
value: 91.2368552829244
task:
type: BitextMining
- dataset:
config: hun_Latn-por_Latn
name: MTEB NTREXBitextMining (hun_Latn-por_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.18978467701552
- type: f1
value: 91.15172759138709
- type: main_score
value: 91.15172759138709
- type: precision
value: 90.19362376898682
- type: recall
value: 93.18978467701552
task:
type: BitextMining
- dataset:
config: hun_Latn-rus_Cyrl
name: MTEB NTREXBitextMining (hun_Latn-rus_Cyrl)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.23835753630446
- type: f1
value: 89.9382406943749
- type: main_score
value: 89.9382406943749
- type: precision
value: 88.85411450509096
- type: recall
value: 92.23835753630446
task:
type: BitextMining
- dataset:
config: hun_Latn-spa_Latn
name: MTEB NTREXBitextMining (hun_Latn-spa_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.34001001502253
- type: f1
value: 91.47888499415792
- type: main_score
value: 91.47888499415792
- type: precision
value: 90.58587881822734
- type: recall
value: 93.34001001502253
task:
type: BitextMining
- dataset:
config: hun_Latn-swa_Latn
name: MTEB NTREXBitextMining (hun_Latn-swa_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 40.76114171256886
- type: f1
value: 32.341475401874824
- type: main_score
value: 32.341475401874824
- type: precision
value: 29.515621549076144
- type: recall
value: 40.76114171256886
task:
type: BitextMining
- dataset:
config: hun_Latn-swe_Latn
name: MTEB NTREXBitextMining (hun_Latn-swe_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.44016024036054
- type: f1
value: 91.490569187114
- type: main_score
value: 91.490569187114
- type: precision
value: 90.56501418794859
- type: recall
value: 93.44016024036054
task:
type: BitextMining
- dataset:
config: hun_Latn-tam_Taml
name: MTEB NTREXBitextMining (hun_Latn-tam_Taml)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 27.591387080620933
- type: f1
value: 18.875023187991868
- type: main_score
value: 18.875023187991868
- type: precision
value: 16.43982939607956
- type: recall
value: 27.591387080620933
task:
type: BitextMining
- dataset:
config: hun_Latn-tur_Latn
name: MTEB NTREXBitextMining (hun_Latn-tur_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.3870806209314
- type: f1
value: 88.90836254381573
- type: main_score
value: 88.90836254381573
- type: precision
value: 87.72325154398266
- type: recall
value: 91.3870806209314
task:
type: BitextMining
- dataset:
config: hun_Latn-vie_Latn
name: MTEB NTREXBitextMining (hun_Latn-vie_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.13670505758637
- type: f1
value: 88.62054987242769
- type: main_score
value: 88.62054987242769
- type: precision
value: 87.41445501585711
- type: recall
value: 91.13670505758637
task:
type: BitextMining
- dataset:
config: hun_Latn-zho_Hant
name: MTEB NTREXBitextMining (hun_Latn-zho_Hant)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.33550325488233
- type: f1
value: 87.71574027708229
- type: main_score
value: 87.71574027708229
- type: precision
value: 86.53861744998451
- type: recall
value: 90.33550325488233
task:
type: BitextMining
- dataset:
config: hun_Latn-zul_Latn
name: MTEB NTREXBitextMining (hun_Latn-zul_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 17.626439659489236
- type: f1
value: 11.826546194507252
- type: main_score
value: 11.826546194507252
- type: precision
value: 10.340822386979896
- type: recall
value: 17.626439659489236
task:
type: BitextMining
- dataset:
config: ind_Latn-hun_Latn
name: MTEB NTREXBitextMining (ind_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.93940911367051
- type: f1
value: 90.91470539142045
- type: main_score
value: 90.91470539142045
- type: precision
value: 89.96411283592055
- type: recall
value: 92.93940911367051
task:
type: BitextMining
- dataset:
config: jpn_Jpan-hun_Latn
name: MTEB NTREXBitextMining (jpn_Jpan-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 88.33249874812218
- type: f1
value: 85.07260891337006
- type: main_score
value: 85.07260891337006
- type: precision
value: 83.54114505090969
- type: recall
value: 88.33249874812218
task:
type: BitextMining
- dataset:
config: kor_Hang-hun_Latn
name: MTEB NTREXBitextMining (kor_Hang-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 86.07911867801702
- type: f1
value: 82.32348522784176
- type: main_score
value: 82.32348522784176
- type: precision
value: 80.59339008512768
- type: recall
value: 86.07911867801702
task:
type: BitextMining
- dataset:
config: lav_Latn-hun_Latn
name: MTEB NTREXBitextMining (lav_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.73610415623435
- type: f1
value: 88.25833989078856
- type: main_score
value: 88.25833989078856
- type: precision
value: 87.09480887998664
- type: recall
value: 90.73610415623435
task:
type: BitextMining
- dataset:
config: lit_Latn-hun_Latn
name: MTEB NTREXBitextMining (lit_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.88783174762143
- type: f1
value: 89.59105324653646
- type: main_score
value: 89.59105324653646
- type: precision
value: 88.49106993824068
- type: recall
value: 91.88783174762143
task:
type: BitextMining
- dataset:
config: nld_Latn-hun_Latn
name: MTEB NTREXBitextMining (nld_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.98948422633951
- type: f1
value: 90.93139709564348
- type: main_score
value: 90.93139709564348
- type: precision
value: 89.93072942747456
- type: recall
value: 92.98948422633951
task:
type: BitextMining
- dataset:
config: pol_Latn-hun_Latn
name: MTEB NTREXBitextMining (pol_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.4371557336004
- type: f1
value: 89.10699382406943
- type: main_score
value: 89.10699382406943
- type: precision
value: 88.00701051577366
- type: recall
value: 91.4371557336004
task:
type: BitextMining
- dataset:
config: por_Latn-hun_Latn
name: MTEB NTREXBitextMining (por_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 92.98948422633951
- type: f1
value: 91.02320146886997
- type: main_score
value: 91.02320146886997
- type: precision
value: 90.09764646970456
- type: recall
value: 92.98948422633951
task:
type: BitextMining
- dataset:
config: rus_Cyrl-hun_Latn
name: MTEB NTREXBitextMining (rus_Cyrl-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.98647971957938
- type: f1
value: 88.3942580537473
- type: main_score
value: 88.3942580537473
- type: precision
value: 87.16992154899015
- type: recall
value: 90.98647971957938
task:
type: BitextMining
- dataset:
config: spa_Latn-hun_Latn
name: MTEB NTREXBitextMining (spa_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.13970956434652
- type: f1
value: 91.19846436321149
- type: main_score
value: 91.19846436321149
- type: precision
value: 90.26456351193457
- type: recall
value: 93.13970956434652
task:
type: BitextMining
- dataset:
config: swa_Latn-hun_Latn
name: MTEB NTREXBitextMining (swa_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 39.05858788182273
- type: f1
value: 33.98323169908456
- type: main_score
value: 33.98323169908456
- type: precision
value: 32.41376425186998
- type: recall
value: 39.05858788182273
task:
type: BitextMining
- dataset:
config: swe_Latn-hun_Latn
name: MTEB NTREXBitextMining (swe_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 93.03955933900852
- type: f1
value: 91.01485561675847
- type: main_score
value: 91.01485561675847
- type: precision
value: 90.04757135703555
- type: recall
value: 93.03955933900852
task:
type: BitextMining
- dataset:
config: tam_Taml-hun_Latn
name: MTEB NTREXBitextMining (tam_Taml-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 27.341011517275916
- type: f1
value: 24.114490363365103
- type: main_score
value: 24.114490363365103
- type: precision
value: 23.01465131730559
- type: recall
value: 27.341011517275916
task:
type: BitextMining
- dataset:
config: tur_Latn-hun_Latn
name: MTEB NTREXBitextMining (tur_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 91.03655483224837
- type: f1
value: 88.4843932565515
- type: main_score
value: 88.4843932565515
- type: precision
value: 87.31180103488568
- type: recall
value: 91.03655483224837
task:
type: BitextMining
- dataset:
config: vie_Latn-hun_Latn
name: MTEB NTREXBitextMining (vie_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.38557836755132
- type: f1
value: 87.73493573693874
- type: main_score
value: 87.73493573693874
- type: precision
value: 86.5005842096478
- type: recall
value: 90.38557836755132
task:
type: BitextMining
- dataset:
config: zho_Hant-hun_Latn
name: MTEB NTREXBitextMining (zho_Hant-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 90.33550325488233
- type: f1
value: 87.59806376231013
- type: main_score
value: 87.59806376231013
- type: precision
value: 86.3253213153063
- type: recall
value: 90.33550325488233
task:
type: BitextMining
- dataset:
config: zul_Latn-hun_Latn
name: MTEB NTREXBitextMining (zul_Latn-hun_Latn)
revision: ed9a4403ed4adbfaf4aab56d5b2709e9f6c3ba33
split: test
type: mteb/NTREX
metrics:
- type: accuracy
value: 17.676514772158235
- type: f1
value: 13.907186347256669
- type: main_score
value: 13.907186347256669
- type: precision
value: 12.923210518264245
- type: recall
value: 17.676514772158235
task:
type: BitextMining
- dataset:
config: rom-hun
name: MTEB RomaTalesBitextMining (rom-hun)
revision: f4394dbca6845743cd33eba77431767b232ef489
split: test
type: kardosdrur/roma-tales
metrics:
- type: accuracy
value: 5.116279069767442
- type: f1
value: 1.8488798023681745
- type: main_score
value: 1.8488798023681745
- type: precision
value: 1.472523686477175
- type: recall
value: 5.116279069767442
task:
type: BitextMining
- dataset:
config: hun_Latn
name: MTEB SIB200Classification (hun_Latn)
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b
split: test
type: mteb/sib200
metrics:
- type: accuracy
value: 68.43137254901961
- type: f1
value: 67.64424216338097
- type: f1_weighted
value: 68.34815340541722
- type: main_score
value: 68.43137254901961
task:
type: Classification
- dataset:
config: hun_Latn
name: MTEB SIB200Classification (hun_Latn)
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b
split: train
type: mteb/sib200
metrics:
- type: accuracy
value: 69.04422253922966
- type: f1
value: 67.9515950437183
- type: f1_weighted
value: 69.07832158763667
- type: main_score
value: 69.04422253922966
task:
type: Classification
- dataset:
config: hun_Latn
name: MTEB SIB200Classification (hun_Latn)
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b
split: validation
type: mteb/sib200
metrics:
- type: accuracy
value: 64.54545454545453
- type: f1
value: 63.78373491440388
- type: f1_weighted
value: 64.98788954233397
- type: main_score
value: 64.54545454545453
task:
type: Classification
- dataset:
config: hun_Latn
name: MTEB SIB200ClusteringS2S (hun_Latn)
revision: a74d7350ea12af010cfb1c21e34f1f81fd2e615b
split: test
type: mteb/sib200
metrics:
- type: main_score
value: 34.91858402487903
- type: v_measure
value: 34.91858402487903
- type: v_measure_std
value: 3.377463869658173
task:
type: Clustering
- dataset:
config: hun-eng
name: MTEB Tatoeba (hun-eng)
revision: 69e8f12da6e31d59addadda9a9c8a2e601a0e282
split: test
type: mteb/tatoeba-bitext-mining
metrics:
- type: accuracy
value: 91.5
- type: f1
value: 89.06666666666666
- type: main_score
value: 89.06666666666666
- type: precision
value: 87.9
- type: recall
value: 91.5
task:
type: BitextMining
tags:
- mteb
paraphrase-multilingual-MiniLM-L12-hu-v2
This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 on the train dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
Model Details
Model Description
- Model Type: Sentence Transformer
- Base model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- Maximum Sequence Length: 128 tokens
- Output Dimensionality: 384 tokens
- Similarity Function: Cosine Similarity
- Training Dataset:
- train
- Language: hu
- License: apache-2.0
Model Sources
- Documentation: Sentence Transformers Documentation
- Repository: Sentence Transformers on GitHub
- Hugging Face: Sentence Transformers on Hugging Face
Full Model Architecture
SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
(1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
Usage
Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
pip install -U sentence-transformers
Then you can load this model and run inference.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("karsar/paraphrase-multilingual-MiniLM-L12-hu-v2")
# Run inference
sentences = [
'Az emberek alszanak.',
'Egy apa és a fia ölelgeti alvás közben.',
'Egy csoport ember ül egy nyitott, térszerű területen, mögötte nagy bokrok és egy sor viktoriánus stílusú épület, melyek közül sokat a kép jobb oldalán lévő erős elmosódás tesz kivehetetlenné.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]
# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]
Evaluation
Metrics
Triplet
- Dataset:
all-nli-dev - Evaluated with
TripletEvaluator
| Metric | Value |
|---|---|
| cosine_accuracy | 0.9918 |
| dot_accuracy | 0.0102 |
| manhattan_accuracy | 0.99 |
| euclidean_accuracy | 0.99 |
| max_accuracy | 0.9918 |
Triplet
- Dataset:
all-nli-test - Evaluated with
TripletEvaluator
| Metric | Value |
|---|---|
| cosine_accuracy | 0.9938 |
| dot_accuracy | 0.008 |
| manhattan_accuracy | 0.9929 |
| euclidean_accuracy | 0.9924 |
| max_accuracy | 0.9938 |
Training Details
Training Dataset
train
- Dataset: train
- Size: 1,044,013 training samples
- Columns:
anchor,positive, andnegative - Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 7 tokens
- mean: 11.73 tokens
- max: 56 tokens
- min: 6 tokens
- mean: 15.24 tokens
- max: 47 tokens
- min: 7 tokens
- mean: 16.07 tokens
- max: 53 tokens
- Samples:
anchor positive negative Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.Egy ember a szabadban, lóháton.Egy ember egy étteremben van, és omlettet rendel.Gyerekek mosolyogva és integetett a kameraGyermekek vannak jelenA gyerekek homlokot rántanakEgy fiú ugrál a gördeszkát a közepén egy piros híd.A fiú gördeszkás trükköt csinál.A fiú korcsolyázik a járdán. - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Evaluation Dataset
train
- Dataset: train
- Size: 5,000 evaluation samples
- Columns:
anchor,positive, andnegative - Approximate statistics based on the first 1000 samples:
anchor positive negative type string string string details - min: 7 tokens
- mean: 11.73 tokens
- max: 56 tokens
- min: 6 tokens
- mean: 15.24 tokens
- max: 47 tokens
- min: 7 tokens
- mean: 16.07 tokens
- max: 53 tokens
- Samples:
anchor positive negative Egy lóháton ülő ember átugrik egy lerombolt repülőgép felett.Egy ember a szabadban, lóháton.Egy ember egy étteremben van, és omlettet rendel.Gyerekek mosolyogva és integetett a kameraGyermekek vannak jelenA gyerekek homlokot rántanakEgy fiú ugrál a gördeszkát a közepén egy piros híd.A fiú gördeszkás trükköt csinál.A fiú korcsolyázik a járdán. - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim" }
Training Hyperparameters
Non-Default Hyperparameters
eval_strategy: stepsper_device_train_batch_size: 128per_device_eval_batch_size: 128num_train_epochs: 1warmup_ratio: 0.1bf16: Truebatch_sampler: no_duplicates
Framework Versions
- Python: 3.11.8
- Sentence Transformers: 3.1.1
- Transformers: 4.44.0
- PyTorch: 2.3.0.post101
- Accelerate: 0.33.0
- Datasets: 3.0.2
- Tokenizers: 0.19.0
Citation
BibTeX
Sentence Transformers
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}