Towards Unified Prompt Tuning for Few-shot Text Classification
This work addresses the challenge of few-shot learning in NLP for researchers and practitioners, offering an incremental improvement by enhancing prompt-based fine-tuning through multi-task pre-training.
The paper tackles the problem of few-shot text classification by introducing the Unified Prompt Tuning (UPT) framework, which improves BERT-style models' performance by pre-training on non-target datasets to capture prompting knowledge, resulting in consistent outperformance over state-of-the-art methods in experiments across various NLP tasks.
Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few-shot learning performance on downstream tasks. It would be desirable if the models can acquire some prompting knowledge before adaptation to specific NLP tasks. We present the Unified Prompt Tuning (UPT) framework, leading to better few-shot text classification for BERT-style models by explicitly capturing prompting semantics from non-target NLP datasets. In UPT, a novel paradigm Prompt-Options-Verbalizer is proposed for joint prompt learning across different NLP tasks, forcing PLMs to capture task-invariant prompting knowledge. We further design a self-supervised task named Knowledge-enhanced Selective Masked Language Modeling to improve the PLM's generalization abilities for accurate adaptation to previously unseen tasks. After multi-task learning across multiple tasks, the PLM can be better prompt-tuned towards any dissimilar target tasks in low-resourced settings. Experiments over a variety of NLP tasks show that UPT consistently outperforms state-of-the-arts for prompt-based fine-tuning.