language: en
tags:
- deberta
- deberta-v3
thumbnail: https://huggingface.co./front/thumbnails/microsoft.png
license: mit
DeBERTa: Decoding-enhanced BERT with Disentangled Attention
DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data.
Please check the official repository for more details and updates.
In DeBERTa V3 we replaced MLM objective with RTD(Replaced Token Detection) objective during pre-training, which significantly improves the model performance. Please check appendix A11 in our paper for more details.
This is the DeBERTa V3 large model with 24 layers, 1024 hidden size. Total parameters is 418M while Embedding layer takes about 131M due to the usage of 128k vocabulary. It's trained with 160GB data.
Fine-tuning on NLU tasks
We present the dev results on SQuAD 1.1/2.0 and MNLI tasks.
| Model | SQuAD 1.1 | SQuAD 2.0 | MNLI-m |
|---|---|---|---|
| RoBERTa-large | 94.6/88.9 | 89.4/86.5 | 90.2 |
| XLNet-large | 95.1/89.7 | 90.6/87.9 | 90.8 |
| DeBERTa-large | -/- | 90.7/88.0 | 91.5 |
| DeBERTa-v3-large | -/- | 91.5/89.0 | 92.0 |
| DeBERTa-v2-xxlarge | 96.1/91.4 | 92.2/89.7 | 91.7 |
Citation
If you find DeBERTa useful for your work, please cite the following paper:
@inproceedings{
he2021deberta,
title={DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=XPZIaotutsD}
}