“UniSumm: Unified Few-Shot Summarization With Multi-Task Pre-Training and Prefix-Tuning”, 2022-11-17 ():
The diverse demands of different summarization tasks and their high annotation costs are driving a need for few-shot summarization. However, despite the emergence of many summarization tasks and datasets, the current training paradigm for few-shot summarization systems ignores potentially shareable knowledge in heterogeneous datasets.
To this end, we propose UniSumm, a unified few-shot summarization BART model pre-trained with multiple summarization tasks and can be prefix-tuned to excel at any few-shot summarization datasets. Meanwhile, to better evaluate few-shot summarization systems, under the principles of diversity and robustness, we assemble and publicize a new benchmark SummZoo. It consists of 8 diverse summarization tasks with multiple sets of few-shot samples for each task, covering both monologue and dialogue domains.
Experimental results and ablation studies show that UniSumm outperforms strong baseline systems by a large margin across all tasks in SummZoo under both automatic and human evaluations.
We release our code and benchmark at Github.