One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification

Xiaoqin Chang, Sophia Yat Mei Lee, Suyang Zhu, Shoushan Li, Guodong Zhou


Abstract
Knowledge distillation is an effective method to transfer knowledge from a large pre-trained teacher model to a compacted student model. However, in previous studies, the distilled student models are still large and remain impractical in highly speed-sensitive systems (e.g., an IR system). In this study, we aim to distill a deep pre-trained model into an extremely compacted shallow model like CNN. Specifically, we propose a novel one-teacher and multiple-student knowledge distillation approach to distill a deep pre-trained teacher model into multiple shallow student models with ensemble learning. Moreover, we leverage large-scale unlabeled data to improve the performance of students. Empirical studies on three sentiment classification tasks demonstrate that our approach achieves better results with much fewer parameters (0.9%-18%) and extremely high speedup ratios (100X-1000X).
Anthology ID:
2022.coling-1.614
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
7042–7052
Language:
URL:
https://aclanthology.org/2022.coling-1.614
DOI:
Bibkey:
Cite (ACL):
Xiaoqin Chang, Sophia Yat Mei Lee, Suyang Zhu, Shoushan Li, and Guodong Zhou. 2022. One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7042–7052, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification (Chang et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.614.pdf