Continual Training of Language Models for Few-Shot Learning

Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, Bing Liu


Abstract
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications. Adapting or posttraining an LM using an unlabeled domain corpus can produce even better performance for end-tasks in the domain. This paper proposes the problem of continually extending an LM by incrementally post-train the LM with a sequence of unlabeled domain corpora to expand its knowledge without forgetting its previous skills. The goal is to improve the few-shot end-task learning in these domains. The resulting system is called CPT (Continual PostTraining), which to our knowledge, is the first continual post-training system. Experimental results verify its effectiveness.
Anthology ID:
2022.emnlp-main.695
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10205–10216
Language:
URL:
https://aclanthology.org/2022.emnlp-main.695
DOI:
Bibkey:
Cite (ACL):
Zixuan Ke, Haowei Lin, Yijia Shao, Hu Xu, Lei Shu, and Bing Liu. 2022. Continual Training of Language Models for Few-Shot Learning. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10205–10216, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Continual Training of Language Models for Few-Shot Learning (Ke et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.695.pdf