‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism

Ronald Cardenas, Bingsheng Yao, Dakuo Wang, Yufang Hou

Abstract: Science journalism refers to the task of reporting technical findings of a scientific paper as a less technical news article to the general public audience. We aim to design an automated system to support this real-world task (ie, automatic science journalism) by 1) introducing a newly-constructed and real-world dataset (SciTechNews), with tuples of a publicly-available scientific paper, its corresponding news article, and an expert-written short summary snippet; 2) proposing a novel technical framework that integrates a paper’s discourse structure with its metadata to guide generation; and, 3) demonstrating with extensive automatic and human experiments that our model outperforms other baseline methods (eg Alpaca and ChatGPT) in elaborating a content plan meaningful for the target audience, simplify the information selected, and produce a coherent final report in a layman’s style.