Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning
This work addresses the challenge of few-shot learning for Chinese NLP tasks, offering a parameter-efficient solution that improves adaptation speed and performance, though it is incremental as it builds on existing prompt tuning and pre-training concepts.
The paper tackles the problem of prompt tuning struggling in few-shot learning by introducing Multi-task Pre-trained Modular Prompt (MP2), which pre-trains combinable prompts on 38 Chinese tasks and selectively activates them for downstream tasks, achieving significant performance gains over existing methods in few-shot settings.
Prompt tuning is a parameter-efficient approach to adapting pre-trained language models to downstream tasks. Although prompt tuning has been shown to match the performance of full model tuning when training data is sufficient, it tends to struggle in few-shot learning settings. In this paper, we present Multi-task Pre-trained Modular Prompt (MP2) to boost prompt tuning for few-shot learning. MP2 is a set of combinable prompts pre-trained on 38 Chinese tasks. On downstream tasks, the pre-trained prompts are selectively activated and combined, leading to strong compositional generalization to unseen tasks. To bridge the gap between pre-training and fine-tuning, we formulate upstream and downstream tasks into a unified machine reading comprehension task. Extensive experiments under two learning paradigms, i.e., gradient descent and black-box tuning, show that MP2 significantly outperforms prompt tuning, full model tuning, and prior prompt pre-training methods in few-shot settings. In addition, we demonstrate that MP2 can achieve surprisingly fast and strong adaptation to downstream tasks by merely learning 8 parameters to combine the pre-trained modular prompts.