Zujie Liang

Zujie Liang

Auto-generated profile, based on publicly available information

Zujie Liang

Ant Group, Shanghai, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021
Verified
Conference Paper
Open access
PDF file
ZLZujie Liang
Zujie Liang
HHHuang Hu
Huang Hu
CXCan Xu
Can Xu
CTChongyang Tao
Chongyang Tao
XGXiubo Geng
Xiubo Geng
DJDaxin Jiang
Daxin Jiang
Zujie Liang, Huang Hu, Can Xu, Chongyang Tao, Xiubo Geng, Yining Chen, Fan Liang, Daxin Jiang. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

21 October 2023
Verified
Conference Paper
Open access
JLJingping Liu
Jingping Liu
TCTao Chen
Tao Chen
ZLZujie Liang
Zujie Liang
HJHaiyun Jiang
Haiyun Jiang
YXYanghua Xiao
Yanghua Xiao
BHBing Han
Bing Han
Prompt tuning has enhanced the performance of Pre-trained Language Models for multi-task learning in few-shot scenarios. However, existing studies fail to consider that the prompts among different layers in Transformer are different due to the diverse information learned at each layer. In general, the bottom layers in the model tend to capture low-level semantic or structural information, while the upper layers primarily acquire task-specific knowledge. Hence, we propose a novel hierarchical prompt tuning model for few-shot multi-task learning to capture this regularity. The designed model mainly consists of three types of prompts: shared prompts, auto-adaptive prompts, and task-specific prompts. Shared prompts facilitate the sharing of general information across all tasks. Auto-adaptive prompts dynamically select and integrate relevant prompt information from all tasks into the current task. Task-specific prompts concentrate on learning task-specific knowledge. To enhance the model's adaptability to diverse inputs, we introduce deep instance-aware language prompts as the foundation for constructing the above prompts. To evaluate the effectiveness of our proposed method, we conduct extensive experiments on multiple widely-used datasets. The experimental results demonstrate that the proposed method achieves state-of-the-art performance for multi-task learning in few-shot settings and outperforms ChatGPT in the full-data setting.