Chinese classical poetry generation LoRA for T5

Junhong Xie; Guangming Xian

doi:10.1117/12.2685033

19 October 2023 Chinese classical poetry generation LoRA for T5

Junhong Xie, Guangming Xian

Proceedings Volume 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023); 1270954 (2023) https://doi.org/10.1117/12.2685033
Event: Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 2023, Nanjing, China

Abstract

Transformer-base language models grow much larger than early. Although large model obtain state-of-the-art performance on various NLP tasks continuously, finetuning billions of parameters cost much time and memories. Inorder to use T5 model for Chinese classical poetry generation without above difficulties, we use LoRA(Low-RankAdaption) to achieve this goal. It shows that we also can use powerful large LMs to solve some less known tasks, andnoneed to change the original parameters of large models.

Citation Download Citation

Junhong Xie and Guangming Xian "Chinese classical poetry generation LoRA for T5", Proc. SPIE 12709, Fourth International Conference on Artificial Intelligence and Electromechanical Automation (AIEA 2023), 1270954 (19 October 2023); https://doi.org/10.1117/12.2685033

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available