asahi417's picture
model update
a9897d7
metadata
datasets:
  - relbert/semeval2012_relational_similarity
model-index:
  - name: relbert/roberta-large-semeval2012-mask-prompt-d-nce-conceptnet-validated
    results:
      - task:
          name: Relation Mapping
          type: sorting-task
        dataset:
          name: Relation Mapping
          args: relbert/relation_mapping
          type: relation-mapping
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.840515873015873
      - task:
          name: Analogy Questions (SAT full)
          type: multiple-choice-qa
        dataset:
          name: SAT full
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6818181818181818
      - task:
          name: Analogy Questions (SAT)
          type: multiple-choice-qa
        dataset:
          name: SAT
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.685459940652819
      - task:
          name: Analogy Questions (BATS)
          type: multiple-choice-qa
        dataset:
          name: BATS
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8076709282934964
      - task:
          name: Analogy Questions (Google)
          type: multiple-choice-qa
        dataset:
          name: Google
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.94
      - task:
          name: Analogy Questions (U2)
          type: multiple-choice-qa
        dataset:
          name: U2
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6535087719298246
      - task:
          name: Analogy Questions (U4)
          type: multiple-choice-qa
        dataset:
          name: U4
          args: relbert/analogy_questions
          type: analogy-questions
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6388888888888888
      - task:
          name: Lexical Relation Classification (BLESS)
          type: classification
        dataset:
          name: BLESS
          args: relbert/lexical_relation_classification
          type: relation-classification
        metrics:
          - name: F1
            type: f1
            value: 0.9281301792978756
          - name: F1 (macro)
            type: f1_macro
            value: 0.9254620165261186
      - task:
          name: Lexical Relation Classification (CogALexV)
          type: classification
        dataset:
          name: CogALexV
          args: relbert/lexical_relation_classification
          type: relation-classification
        metrics:
          - name: F1
            type: f1
            value: 0.8856807511737088
          - name: F1 (macro)
            type: f1_macro
            value: 0.7505936116426153
      - task:
          name: Lexical Relation Classification (EVALution)
          type: classification
        dataset:
          name: BLESS
          args: relbert/lexical_relation_classification
          type: relation-classification
        metrics:
          - name: F1
            type: f1
            value: 0.7210184182015169
          - name: F1 (macro)
            type: f1_macro
            value: 0.707381518416115
      - task:
          name: Lexical Relation Classification (K&H+N)
          type: classification
        dataset:
          name: K&H+N
          args: relbert/lexical_relation_classification
          type: relation-classification
        metrics:
          - name: F1
            type: f1
            value: 0.9625791194268624
          - name: F1 (macro)
            type: f1_macro
            value: 0.8830231594217628
      - task:
          name: Lexical Relation Classification (ROOT09)
          type: classification
        dataset:
          name: ROOT09
          args: relbert/lexical_relation_classification
          type: relation-classification
        metrics:
          - name: F1
            type: f1
            value: 0.9207145095581323
          - name: F1 (macro)
            type: f1_macro
            value: 0.9189981669115016

relbert/roberta-large-semeval2012-mask-prompt-d-nce-conceptnet-validated

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): 0.6818181818181818
    • Accuracy on SAT: 0.685459940652819
    • Accuracy on BATS: 0.8076709282934964
    • Accuracy on U2: 0.6535087719298246
    • Accuracy on U4: 0.6388888888888888
    • Accuracy on Google: 0.94
  • Lexical Relation Classification (dataset, full result):
    • Micro F1 score on BLESS: 0.9281301792978756
    • Micro F1 score on CogALexV: 0.8856807511737088
    • Micro F1 score on EVALution: 0.7210184182015169
    • Micro F1 score on K&H+N: 0.9625791194268624
    • Micro F1 score on ROOT09: 0.9207145095581323
  • Relation Mapping (dataset, full result):
    • Accuracy on Relation Mapping: 0.840515873015873

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-mask-prompt-d-nce-conceptnet-validated")
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: mask
  • data: relbert/semeval2012_relational_similarity
  • split: train
  • data_eval: relbert/conceptnet_high_confidence
  • split_eval: full
  • template_mode: manual
  • template: I wasn’t aware of this relationship, but I just read in the encyclopedia that is the
  • loss_function: nce_logout
  • classification_loss: False
  • temperature_nce_constant: 0.05
  • temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
  • epoch: 25
  • 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",
}