Zujie Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Zujie Liang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Bing Han
MYbank, Ant Group
1 shared publication - Can Xu
Google, USA
1 shared publication - Chongyang Tao
Beihang University
1 shared publication - Daxin Jiang
StepFun, Shanghai, China
1 shared publication Fan Liang
School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China
1 shared publication- Feng Wei
Ant Group, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1556-1565
Hierarchical Prompt Tuning for Few-Shot Multi-Task Learning
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.
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1556-1565
Open AccessHierarchical Prompt Tuning for Few-Shot Multi-Task Learning
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.
- Open Access
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 5596-5611
Maria: A Visual Experience Powered Conversational Agent
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.
- 1 January 2021
- Published by Association for Computational Linguistics (ACL)
- p. 5596-5611
Open AccessMaria: A Visual Experience Powered Conversational Agent
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.