metadata
datasets:
- relbert/semeval2012_relational_similarity_v6
model-index:
- name: relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-0
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: 0.6770238095238095
- 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: 0.32887700534759357
- 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: 0.33827893175074186
- 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: 0.48360200111172874
- 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: 0.49
- 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: 0.3684210526315789
- 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: 0.35648148148148145
- 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: 0.8271809552508663
- name: F1 (macro)
type: f1_macro
value: 0.8139940994079059
- 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: 0.7927230046948357
- name: F1 (macro)
type: f1_macro
value: 0.47757376520100464
- 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: 0.5866738894907909
- name: F1 (macro)
type: f1_macro
value: 0.5099661171290004
- 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: 0.8843291368157474
- name: F1 (macro)
type: f1_macro
value: 0.7260666016287155
- 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: 0.8335944844876215
- name: F1 (macro)
type: f1_macro
value: 0.8285945038843159
relbert/relbert-roberta-base-semeval2012-v6-mask-prompt-b-triplet-0
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): 0.32887700534759357
- Accuracy on SAT: 0.33827893175074186
- Accuracy on BATS: 0.48360200111172874
- Accuracy on U2: 0.3684210526315789
- Accuracy on U4: 0.35648148148148145
- Accuracy on Google: 0.49
- Lexical Relation Classification (dataset, full result):
- Micro F1 score on BLESS: 0.8271809552508663
- Micro F1 score on CogALexV: 0.7927230046948357
- Micro F1 score on EVALution: 0.5866738894907909
- Micro F1 score on K&H+N: 0.8843291368157474
- Micro F1 score on ROOT09: 0.8335944844876215
- Relation Mapping (dataset, full result):
- Accuracy on Relation Mapping: 0.6770238095238095
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-b-triplet-0")
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"
- template: "Today, I finally discovered the relation between and : is 's
- loss_function: "triplet"
- classification_loss: "False"
- temperature_nce_constant: "0.05"
- temperature_nce_rank: "{'min': 0.01, 'max': 0.05, 'type': 'linear'}"
- epoch: "8"
- batch: "128"
- lr: "5e-06"
- lr_decay: "False"
- lr_warmup: "1"
- weight_decay: "0"
- random_seed: "0"
- exclude_relation: "None"
- n_sample: "320"
- gradient_accumulation: "8"
- relation_level: "None"
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",
}