relbert/relbert-roberta-base-semeval2012-v6-average-prompt-e-nce-0-parent

• Analogy Question (dataset, full result):
  • Accuracy on SAT (full): 0.45989304812834225
  • Accuracy on SAT: 0.4629080118694362
  • Accuracy on BATS: 0.565869927737632
  • Accuracy on U2: 0.41228070175438597
  • Accuracy on U4: 0.4699074074074074
  • Accuracy on Google: 0.744
• Lexical Relation Classification (dataset, full result):
  • Micro F1 score on BLESS: 0.8999547988549043
  • Micro F1 score on CogALexV: 0.8105633802816902
  • Micro F1 score on EVALution: 0.6164680390032503
  • Micro F1 score on K&H+N: 0.9581971204006399
  • Micro F1 score on ROOT09: 0.8834221247257913
• Relation Mapping (dataset, full result):
  • Accuracy on Relation Mapping: 0.7812301587301588

Usage

Training hyperparameters

• model: roberta-base
• max_length: 64
• mode: average
• data: relbert/semeval2012_relational_similarity_v6
• split: train
• split_eval: validation
• template_mode: manual
• loss_function: nce_logout
• classification_loss: False
• temperature_nce_constant: 0.05
• temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
• epoch: 10
• batch: 128
• lr: 5e-06
• lr_decay: False
• lr_warmup: 1
• weight_decay: 0
• random_seed: 0
• exclude_relation: None
• n_sample: 320
• gradient_accumulation: 8
• relation_level: None
• data_level: parent

Reference

@inproceedings{ushio-etal-2021-distilling-relation-embeddings,
    title = "{D}istilling {R}elation {E}mbeddings from {P}re-trained {L}anguage {M}odels",
    author = "Ushio, Asahi  and
      Schockaert, Steven  and
      Camacho-Collados, Jose",
    booktitle = "EMNLP 2021",
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
}