Edit model card

relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-d-loob-2-child

RelBERT fine-tuned from roberta-base on
relbert/semeval2012_relational_similarity_v6. Fine-tuning is done via RelBERT library (see the repository for more detail). It achieves the following results on the relation understanding tasks:

  • Analogy Question (dataset, full result):
    • Accuracy on SAT (full): 0.47593582887700536
    • Accuracy on SAT: 0.47477744807121663
    • Accuracy on BATS: 0.6753752084491385
    • Accuracy on U2: 0.43859649122807015
    • Accuracy on U4: 0.4537037037037037
    • Accuracy on Google: 0.868
  • Lexical Relation Classification (dataset, full result):
    • Micro F1 score on BLESS: 0.9029682085279493
    • Micro F1 score on CogALexV: 0.8276995305164319
    • Micro F1 score on EVALution: 0.6522210184182016
    • Micro F1 score on K&H+N: 0.9555540098768867
    • Micro F1 score on ROOT09: 0.872453776245691
  • Relation Mapping (dataset, full result):
    • Accuracy on Relation Mapping: 0.7243055555555555

Usage

This model can be used through the relbert library. Install the library via pip

pip install relbert

and activate model as below.

from relbert import RelBERT
model = RelBERT("relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-d-loob-2-child")
vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (1024, )

Training hyperparameters

The following hyperparameters were used during training:

  • model: roberta-base
  • max_length: 64
  • mode: mask
  • data: relbert/semeval2012_relational_similarity_v6
  • split: train
  • split_eval: validation
  • template_mode: manual
  • loss_function: info_loob
  • classification_loss: False
  • temperature_nce_constant: 0.05
  • temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
  • epoch: 9
  • 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

The full configuration can be found at fine-tuning parameter file.

Reference

If you use any resource from RelBERT, please consider to cite our paper.


@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",
}
Downloads last month
9

Dataset used to train research-backup/relbert-roberta-base-semeval2012-v6-mask-prompt-d-loob-2-child

Evaluation results