README.md

metadata

datasets:
  - semeval2012
model-index:
  - name: relbert/roberta-large-semeval2012-average-prompt-b-triplet
    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: 0.815952380952381
      - 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: 0.5748663101604278
      - 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: 0.5756676557863502
      - 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: 0.7809894385769872
      - 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: 0.87
      - 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: 0.5570175438596491
      - 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: 0.5763888888888888
      - 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: 0.9156245291547386
          - name: F1 (macro)
            type: f1_macro
            value: 0.9123138480377561
      - 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: 0.8652582159624412
          - name: F1 (macro)
            type: f1_macro
            value: 0.7098768153077847
      - 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: 0.6765980498374865
          - name: F1 (macro)
            type: f1_macro
            value: 0.667723188418867
      - 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: 0.9621617861862697
          - name: F1 (macro)
            type: f1_macro
            value: 0.8800726259971795
      - 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: 0.8925101848950172
          - name: F1 (macro)
            type: f1_macro
            value: 0.8890641447568232

relbert/roberta-large-semeval2012-average-prompt-b-triplet

RelBERT fine-tuned from roberta-large on
semeval2012. 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): 0.5748663101604278
  • Accuracy on SAT: 0.5756676557863502
  • Accuracy on BATS: 0.7809894385769872
  • Accuracy on U2: 0.5570175438596491
  • Accuracy on U4: 0.5763888888888888
  • Accuracy on Google: 0.87
• Lexical Relation Classification (dataset, full result):
  • Micro F1 score on BLESS: 0.9156245291547386
  • Micro F1 score on CogALexV: 0.8652582159624412
  • Micro F1 score on EVALution: 0.6765980498374865
  • Micro F1 score on K&H+N: 0.9621617861862697
  • Micro F1 score on ROOT09: 0.8925101848950172
• Relation Mapping (dataset, full result):
  • Accuracy on Relation Mapping: 0.815952380952381

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-triplet")
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: semeval2012
• n_sample: 10
• custom_template: Today, I finally discovered the relation between and : is 's
• template: None
• softmax_loss: True
• in_batch_negative: True
• parent_contrast: True
• mse_margin: 1
• epoch: 1
• lr_warmup: 10
• batch: 64
• lr: 2e-05
• lr_decay: False
• weight_decay: 0
• optimizer: adam
• momentum: 0.9
• fp16: False
• random_seed: 0

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",
}