Learning to Initialize: Can Meta Learning Improve Cross-task Generalization in Prompt Tuning?
This addresses the challenge of few-shot learning efficiency for NLP practitioners, but it is incremental as it builds on existing prompt tuning and meta-learning methods.
The paper tackles the problem of prompt tuning's heavy reliance on good initialization by exploring meta-learning to improve cross-task generalization through learned prompt embeddings, showing significant improvements on classification tasks and mixed results on question answering compared to multi-task learning.
Prompt tuning (PT) which only tunes the embeddings of an additional sequence of tokens per task, keeping the pre-trained language model (PLM) frozen, has shown remarkable performance in few-shot learning. Despite this, PT has been shown to rely heavily on good initialization of the prompt embeddings. In this work, we study meta prompt tuning (MPT) to systematically explore how meta-learning can help improve (if it can) cross-task generalization in PT through learning to initialize the prompt embeddings from other relevant tasks. We empirically analyze a representative set of meta learning algorithms in a wide range of adaptation settings with different source/target task configurations on a large set of few-shot tasks. With extensive experiments and analysis, we demonstrate the effectiveness of MPT. We find the improvement to be significant particularly on classification tasks. For other kinds of tasks such as question answering, we observe that while MPT can outperform PT in most cases, it does not always outperform multi-task learning. We further provide an in-depth analysis from the perspective of task similarity.