Accelerating BERT Inference for Sequence Labeling via Early-Exit

Xiaonan Li, Yunfan Shao, Tianxiang Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang


Abstract
Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their computational cost is expensive. To alleviate this problem, we extend the recent successful early-exit mechanism to accelerate the inference of PTMs for sequence labeling tasks. However, existing early-exit mechanisms are specifically designed for sequence-level tasks, rather than sequence labeling. In this paper, we first propose a simple extension of sentence-level early-exit for sequence labeling tasks. To further reduce the computational cost, we also propose a token-level early-exit mechanism that allows partial tokens to exit early at different layers. Considering the local dependency inherent in sequence labeling, we employed a window-based criterion to decide for a token whether or not to exit. The token-level early-exit brings the gap between training and inference, so we introduce an extra self-sampling fine-tuning stage to alleviate it. The extensive experiments on three popular sequence labeling tasks show that our approach can save up to 66%∼75% inference cost with minimal performance degradation. Compared with competitive compressed models such as DistilBERT, our approach can achieve better performance under the same speed-up ratios of 2×, 3×, and 4×.
Anthology ID:
2021.acl-long.16
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
189–199
Language:
URL:
https://aclanthology.org/2021.acl-long.16
DOI:
10.18653/v1/2021.acl-long.16
Bibkey:
Cite (ACL):
Xiaonan Li, Yunfan Shao, Tianxiang Sun, Hang Yan, Xipeng Qiu, and Xuanjing Huang. 2021. Accelerating BERT Inference for Sequence Labeling via Early-Exit. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 189–199, Online. Association for Computational Linguistics.
Cite (Informal):
Accelerating BERT Inference for Sequence Labeling via Early-Exit (Li et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.16.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.acl-long.16.mp4
Code
 LeeSureman/Sequence-Labeling-Early-Exit
Data
CLUECoNLL-2003Universal Dependencies