Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization

Anonymous

Abstract: Content-Controllable Summarization generates summaries focusing on the given controlling signals. We propose a plug-and-play module RelAttn to adapt any general summarizers to the content-controllable summarization task in zero- or few-shot settings. RelAttn first identifies the relevant content in the source documents, and then guides the model to attend to the appropriate context by directly steering the attention weight. We further propose an unsupervised online adaptive parameter searching algorithm to determine the degree of control in the zero-shot setting, while such parameters are learned in the few-shot setting. Experiments on three backbone models show that our method effectively improves all the summarizers, and outperforms both the prompting-based method and a widely used plug-and-play model.

Paper Type: long

Research Area: Summarization

Contribution Types: Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.