BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance

Jianquan Li, Xiaokang Liu, Honghong Zhao, Ruifeng Xu, Min Yang, Yaohong Jin


Abstract
Pre-trained language models (e.g., BERT) have achieved significant success in various natural language processing (NLP) tasks. However, high storage and computational costs obstruct pre-trained language models to be effectively deployed on resource-constrained devices. In this paper, we propose a novel BERT distillation method based on many-to-many layer mapping, which allows each intermediate student layer to learn from any intermediate teacher layers. In this way, our model can learn from different teacher layers adaptively for different NLP tasks. In addition, we leverage Earth Mover’s Distance (EMD) to compute the minimum cumulative cost that must be paid to transform knowledge from teacher network to student network. EMD enables effective matching for the many-to-many layer mapping. Furthermore, we propose a cost attention mechanism to learn the layer weights used in EMD automatically, which is supposed to further improve the model’s performance and accelerate convergence time. Extensive experiments on GLUE benchmark demonstrate that our model achieves competitive performance compared to strong competitors in terms of both accuracy and model compression
Anthology ID:
2020.emnlp-main.242
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3009–3018
Language:
URL:
https://aclanthology.org/2020.emnlp-main.242
DOI:
10.18653/v1/2020.emnlp-main.242
Bibkey:
Cite (ACL):
Jianquan Li, Xiaokang Liu, Honghong Zhao, Ruifeng Xu, Min Yang, and Yaohong Jin. 2020. BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3009–3018, Online. Association for Computational Linguistics.
Cite (Informal):
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover’s Distance (Li et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.242.pdf
Video:
 https://slideslive.com/38938812
Code
 lxk00/BERT-EMD
Data
GLUEQNLI