Curriculum Learning for Natural Language Understanding

Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, Yongdong Zhang


Abstract
With the great success of pre-trained language models, the pretrain-finetune paradigm now becomes the undoubtedly dominant solution for natural language understanding (NLU) tasks. At the fine-tune stage, target task data is usually introduced in a completely random order and treated equally. However, examples in NLU tasks can vary greatly in difficulty, and similar to human learning procedure, language models can benefit from an easy-to-difficult curriculum. Based on this idea, we propose our Curriculum Learning approach. By reviewing the trainset in a crossed way, we are able to distinguish easy examples from difficult ones, and arrange a curriculum for language models. Without any manual model architecture design or use of external data, our Curriculum Learning approach obtains significant and universal performance improvements on a wide range of NLU tasks.
Anthology ID:
2020.acl-main.542
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6095–6104
Language:
URL:
https://aclanthology.org/2020.acl-main.542
DOI:
10.18653/v1/2020.acl-main.542
Bibkey:
Cite (ACL):
Benfeng Xu, Licheng Zhang, Zhendong Mao, Quan Wang, Hongtao Xie, and Yongdong Zhang. 2020. Curriculum Learning for Natural Language Understanding. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6095–6104, Online. Association for Computational Linguistics.
Cite (Informal):
Curriculum Learning for Natural Language Understanding (Xu et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nodalida-main-page/2020.acl-main.542.pdf
Video:
 http://slideslive.com/38929322