SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning
Bari, M Saiful, Zhang, Aston, Zheng, Shuai, Shi, Xingjian, Zhu, Yi, Joty, Shafiq, Li, Mu
–arXiv.org Artificial Intelligence
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way. Multitask prompted learning can help generalization through a diverse set of tasks at once, thus enhancing the potential for more effective downstream fine-tuning. To perform efficient multitask-inference in the same batch, parameter-efficient fine-tuning methods such as prompt tuning have been proposed. However, the existing prompt tuning methods may lack generalization. We propose SPT, a semi-parametric prompt tuning method for multitask prompted learning. The novel component of SPT is a memory bank from where memory prompts are retrieved based on discrete prompts. Extensive experiments, such as (i) fine-tuning a full language model with SPT on 31 different tasks from 8 different domains and evaluating zero-shot generalization on 9 heldout datasets under 5 NLP task categories and (ii) pretraining SPT on the GLUE datasets and evaluating fine-tuning on the SuperGLUE datasets, demonstrate effectiveness of SPT.
arXiv.org Artificial Intelligence
Dec-21-2022
- Country:
- Africa (0.14)
- North America
- Dominican Republic (0.04)
- United States
- Minnesota > Hennepin County
- Minneapolis (0.14)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Minnesota > Hennepin County
- Canada > Quebec
- Montreal (0.04)
- Europe
- Romania > Sud - Muntenia Development Region
- Giurgiu County > Giurgiu (0.04)
- Italy > Calabria
- Catanzaro Province > Catanzaro (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Romania > Sud - Muntenia Development Region
- Asia > Middle East
- Jordan (0.04)
- Genre:
- Research Report (0.40)
- Industry:
- Leisure & Entertainment > Sports > Soccer (0.46)
- Technology: