Learning to Transfer Prompts for Text Generation

TL;DR

This paper introduces PTG, a prompt-based transfer learning method for text generation that leverages source prompts and adaptive attention to improve performance in data-scarce scenarios, outperforming traditional fine-tuning.

Contribution

It proposes a novel prompt transfer approach with adaptive attention, enabling effective transfer of prompts across tasks for improved text generation.

Findings

PTG achieves competitive or superior results compared to fine-tuning.

The method effectively transfers prompts across tasks with limited data.

Open source release of prompts facilitates future research.

Abstract

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and lightweight model that can adapt to various text generation tasks based on PLMs. To fulfill this purpose, the recent prompt-based learning offers a potential solution. In this paper, we improve this technique and propose a novel prompt-based method (PTG) for text generation in a transferable setting. First, PTG learns a set of source prompts for various source generation tasks and then transfers these prompts as target prompts to perform target generation tasks. To consider both task- and instance-level information, we design an adaptive attention mechanism to derive the target prompts. For each data instance, PTG learns a specific target prompt by attending to highly relevant source prompts. In extensive experiments, PTG yields competitive or better results than fine-tuning methods. We release our source prompts as an open resource, where users can add or reuse them to improve new text generation tasks for future research. Code and data can be available at https://github.com/RUCAIBox/Transfer-Prompts-for-Text-Generation.