relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-2-child-prototypical

• Analogy Question (dataset, full result):
  • Accuracy on SAT (full): 0.3315508021390374
  • Accuracy on SAT: 0.33827893175074186
  • Accuracy on BATS: 0.3941078376876042
  • Accuracy on U2: 0.40350877192982454
  • Accuracy on U4: 0.38425925925925924
  • Accuracy on Google: 0.476
• Lexical Relation Classification (dataset, full result):
  • Micro F1 score on BLESS: 0.8157299984932952
  • Micro F1 score on CogALexV: 0.7908450704225352
  • Micro F1 score on EVALution: 0.5390032502708559
  • Micro F1 score on K&H+N: 0.9006746887389581
  • Micro F1 score on ROOT09: 0.8097774992165465
• Relation Mapping (dataset, full result):
  • Accuracy on Relation Mapping: 0.6994047619047619

Usage

Training hyperparameters

• model: roberta-base
• max_length: 64
• mode: mask
• data: relbert/semeval2012_relational_similarity_v6
• split: train
• split_eval: validation
• template_mode: manual
• loss_function: triplet
• classification_loss: False
• temperature_nce_constant: 0.05
• temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
• epoch: 8
• batch: 128
• lr: 5e-06
• lr_decay: False
• lr_warmup: 1
• weight_decay: 0
• random_seed: 2
• exclude_relation: None
• n_sample: 320
• gradient_accumulation: 8
• relation_level: None
• data_level: child_prototypical

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",
}