Edit model card

relbert/roberta-large-semeval2012-average-no-mask-prompt-c-nce-classification

RelBERT fine-tuned from roberta-large on
relbert/semeval2012_relational_similarity. 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): 0.29411764705882354
    • Accuracy on SAT: 0.29080118694362017
    • Accuracy on BATS: 0.4641467481934408
    • Accuracy on U2: 0.32456140350877194
    • Accuracy on U4: 0.3449074074074074
    • Accuracy on Google: 0.614
  • Lexical Relation Classification (dataset, full result):
    • Micro F1 score on BLESS: 0.8862437848425494
    • Micro F1 score on CogALexV: 0.8370892018779342
    • Micro F1 score on EVALution: 0.5384615384615384
    • Micro F1 score on K&H+N: 0.9659177853516032
    • Micro F1 score on ROOT09: 0.8567847069884049
  • Relation Mapping (dataset, full result):
    • Accuracy on Relation Mapping: 0.7127976190476191

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/roberta-large-semeval2012-average-no-mask-prompt-c-nce-classification")
vector = model.get_embedding(['Tokyo', 'Japan'])  # shape of (1024, )

Training hyperparameters

The following hyperparameters were used during training:

  • model: roberta-large
  • max_length: 64
  • mode: average_no_mask
  • data: relbert/semeval2012_relational_similarity
  • split: train
  • data_eval: relbert/conceptnet_high_confidence
  • split_eval: full
  • template_mode: manual
  • template: Today, I finally discovered the relation between and :
  • loss_function: nce_logout
  • classification_loss: True
  • temperature_nce_constant: 0.05
  • temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
  • epoch: 1
  • batch: 128
  • lr: 5e-06
  • lr_decay: False
  • lr_warmup: 1
  • weight_decay: 0
  • random_seed: 0
  • exclude_relation: None
  • exclude_relation_eval: None
  • n_sample: 640
  • gradient_accumulation: 8

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
7

Dataset used to train research-backup/roberta-large-semeval2012-average-no-mask-prompt-c-nce-classification

Evaluation results