README.md

metadata

datasets:
  - relbert/semeval2012_relational_similarity
model-index:
  - name: >-
      relbert/roberta-large-semeval2012-average-prompt-b-nce-classification-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: 0.8433333333333334
      - 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: 0.4732620320855615
      - 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: 0.49258160237388726
      - 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: 0.5986659255141745
      - 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: 0.686
      - 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: 0.44298245614035087
      - 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: 0.4930555555555556
      - 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: 0.9085430164230828
          - name: F1 (macro)
            type: f1_macro
            value: 0.9029499017420614
      - 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: 0.8359154929577466
          - name: F1 (macro)
            type: f1_macro
            value: 0.6401332628753275
      - 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: 0.6581798483206934
          - name: F1 (macro)
            type: f1_macro
            value: 0.6411620033399844
      - 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: 0.9586840091813313
          - name: F1 (macro)
            type: f1_macro
            value: 0.8809925441051085
      - 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: 0.8824819805703541
          - name: F1 (macro)
            type: f1_macro
            value: 0.877314171779575

relbert/roberta-large-semeval2012-average-prompt-b-nce-classification-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): 0.4732620320855615
  • Accuracy on SAT: 0.49258160237388726
  • Accuracy on BATS: 0.5986659255141745
  • Accuracy on U2: 0.44298245614035087
  • Accuracy on U4: 0.4930555555555556
  • Accuracy on Google: 0.686
• Lexical Relation Classification (dataset, full result):
  • Micro F1 score on BLESS: 0.9085430164230828
  • Micro F1 score on CogALexV: 0.8359154929577466
  • Micro F1 score on EVALution: 0.6581798483206934
  • Micro F1 score on K&H+N: 0.9586840091813313
  • Micro F1 score on ROOT09: 0.8824819805703541
• Relation Mapping (dataset, full result):
  • Accuracy on Relation Mapping: 0.8433333333333334

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-prompt-b-nce-classification-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: average
• 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 : is 's
• loss_function: nce_logout
• classification_loss: True
• temperature_nce_constant: 0.05
• temperature_nce_rank: {'min': 0.01, 'max': 0.05, 'type': 'linear'}
• epoch: 30
• 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",
}