Improving task generalization via unified schema prompt

Improving task generalization via unified schema prompt

Task generalization has been a long-standing challenge in Natural Language Processing (NLP). Recent research attempts to improve the task generalization ability of pre-trained language models by mapping NLP tasks into human-readable prompted forms. However, these approaches require laborious and inf...

Full description

Bibliographic Details
Main Authors: Wanjun Zhong, Yifan Gao, Ning Ding, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2023-01-01
Series:AI Open
Subjects:
Prompting
Language model
Natural language processing
Multi-task
Online Access:http://www.sciencedirect.com/science/article/pii/S266665102300013X

Internet

http://www.sciencedirect.com/science/article/pii/S266665102300013X

Similar Items