ILKT

/

2024-06-19_22-27-15

like 0

Follow

Inter-Lingual Knowledge Transfer 4

Evaluation results

• accuracy on MTEB AllegroReviews (default)
  test set self-reported
  21.014
• f1 on MTEB AllegroReviews (default)
  test set self-reported
  19.340
• accuracy on MTEB CBD (default)
  test set self-reported
  53.690
• ap on MTEB CBD (default)
  test set self-reported
  13.997
• f1 on MTEB CBD (default)
  test set self-reported
  44.207
• v_measure on MTEB EightTagsClustering (default)
  test set self-reported
  2.969
• v_measure_std on MTEB EightTagsClustering (default)
  test set self-reported
  0.840
• accuracy on MTEB MassiveIntentClassification (pl)
  test set self-reported
  22.683
• f1 on MTEB MassiveIntentClassification (pl)
  test set self-reported
  19.515
• accuracy on MTEB MassiveIntentClassification (pl)
  validation set self-reported
  21.687
• f1 on MTEB MassiveIntentClassification (pl)
  validation set self-reported
  18.765
• accuracy on MTEB MassiveScenarioClassification (pl)
  test set self-reported
  27.007
• f1 on MTEB MassiveScenarioClassification (pl)
  test set self-reported
  24.362
• accuracy on MTEB MassiveScenarioClassification (pl)
  validation set self-reported
  26.173
• f1 on MTEB MassiveScenarioClassification (pl)
  validation set self-reported
  24.251
• accuracy on MTEB PAC (default)
  test set self-reported
  52.592
• ap on MTEB PAC (default)
  test set self-reported
  70.164
• f1 on MTEB PAC (default)
  test set self-reported
  51.706
• v_measure on MTEB PlscClusteringP2P (default)
  test set self-reported
  26.202
• v_measure on MTEB PlscClusteringS2S (default)
  test set self-reported
  18.794