|
--- |
|
language: en |
|
tags: deberta |
|
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png |
|
license: mit |
|
--- |
|
|
|
## DeBERTa: Decoding-enhanced BERT with Disentangled Attention |
|
|
|
[DeBERTa](https://arxiv.org/abs/2006.03654) 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](https://github.com/microsoft/DeBERTa) for more details and updates. |
|
|
|
This is the DeBERTa V3 small model with 6 layers, 768 hidden size. Total parameters is 143M while Embedding layer take about 98M due to the usage of 128k vocabulary. It's trained with 160GB data. |
|
For more details of our V3 model, please check appendix A11 in our paper. |
|
|
|
#### 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-base | 91.5/84.6 | 83.7/80.5 | 87.6 | |
|
| XLNet-base | -/- | -/80.2 | 86.8 | |
|
| **DeBERTa-v3-small** | 93.1/87.2 | 86.2/83.1 | 88.2 | |
|
|
|
|
|
### Citation |
|
|
|
If you find DeBERTa useful for your work, please cite the following paper: |
|
|
|
``` latex |
|
@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} |
|
} |
|
``` |
|
|
