relbert/roberta-large-semeval2012-mask-prompt-d-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): 0.6122994652406417
- Accuracy on SAT: 0.6231454005934718
- Accuracy on BATS: 0.7665369649805448
- Accuracy on U2: 0.6096491228070176
- Accuracy on U4: 0.6388888888888888
- Accuracy on Google: 0.948
- Lexical Relation Classification (dataset, full result):
- Micro F1 score on BLESS: 0.9065843001356034
- Micro F1 score on CogALexV: 0.8814553990610329
- Micro F1 score on EVALution: 0.7193932827735645
- Micro F1 score on K&H+N: 0.9527022327328372
- Micro F1 score on ROOT09: 0.900658100908806
- Relation Mapping (dataset, full result):
- Accuracy on Relation Mapping: 0.8038492063492063
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-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: mask
- data: semeval2012
- n_sample: 10
- custom_template: I wasn’t aware of this relationship, but I just read in the encyclopedia that <subj> is the <mask> of <obj>
- 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",
}