ILKT

/

2024-06-19_21-12-17

like 0

Follow

Inter-Lingual Knowledge Transfer 4

Evaluation results

• accuracy on MTEB MassiveIntentClassification
  test set self-reported
  0.119
• accuracy on MTEB MassiveIntentClassification
  validation set self-reported
  0.116
• accuracy on MTEB MassiveScenarioClassification
  test set self-reported
  0.212
• accuracy on MTEB MassiveScenarioClassification
  validation set self-reported
  0.200
• accuracy on MTEB CBD
  test set self-reported
  0.521
• accuracy on MTEB PolEmo2.0-IN
  test set self-reported
  0.355
• accuracy on MTEB PolEmo2.0-OUT
  test set self-reported
  0.298
• accuracy on MTEB AllegroReviews
  test set self-reported
  0.222
• accuracy on MTEB PAC
  test set self-reported
  0.554
• v_measure on MTEB EightTagsClustering
  test set self-reported
  0.070
• ap on MTEB SICK-E-PL
  test set self-reported
  0.437
• ap on MTEB CDSC-E
  test set self-reported
  0.412
• ap on MTEB PSC
  test set self-reported
  0.383
• cosine_spearman on MTEB STS22
  test set self-reported
  -0.031
• cosine_spearman on MTEB STSBenchmarkMultilingualSTS
  self-reported
  0.297
• cosine_spearman on MTEB STSBenchmarkMultilingualSTS
  test set self-reported
  0.304
• cosine_spearman on MTEB SICK-R-PL
  test set self-reported
  0.276
• cosine_spearman on MTEB CDSC-R
  test set self-reported
  0.302
• v_measure on MTEB PlscClusteringS2S
  test set self-reported
  0.249
• v_measure on MTEB PlscClusteringP2P
  test set self-reported
  0.192