English

PromptSum: Parameter-Efficient Controllable Abstractive Summarization

Computation and Language 2023-08-08 v1

Abstract

Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown promising results in language understanding tasks, especially in low-resource scenarios. However, effective prompt design methods suitable for generation tasks such as summarization are still lacking. At the same time, summarization guided through instructions (discrete prompts) can achieve a desirable double objective of high quality and controllability in summary generation. Towards a goal of strong summarization performance under the triple conditions of parameter-efficiency, data-efficiency, and controllability, we introduce PromptSum, a method combining PT with a multi-task objective and discrete entity prompts for abstractive summarization. Our model achieves competitive ROUGE results on popular abstractive summarization benchmarks coupled with a strong level of controllability through entities, all while only tuning several orders of magnitude less parameters.

Keywords

Cite

@article{arxiv.2308.03117,
  title  = {PromptSum: Parameter-Efficient Controllable Abstractive Summarization},
  author = {Mathieu Ravaut and Hailin Chen and Ruochen Zhao and Chengwei Qin and Shafiq Joty and Nancy Chen},
  journal= {arXiv preprint arXiv:2308.03117},
  year   = {2023}
}