@article{Dangovski_Shen_Byrd_Jing_Tsvetkova_Nakov_Soljačić_2021, title={We Can Explain Your Research in Layman’s Terms: Towards Automating Science Journalism at Scale}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17507}, DOI={10.1609/aaai.v35i14.17507}, abstractNote={We propose to study Automating Science Journalism (ASJ), the process of producing a layman’s terms summary of a research article, as a new benchmark for long neural abstractive summarization and story generation. Automating science journalism is a challenging task as it requires paraphrasing complex scientific concepts to be grasped by the general public. Thus, we create a specialized dataset that contains scientific papers and their Science Daily press releases. We demonstrate numerous sequence to sequence (seq2seq) applications using Science Daily with the aim of facilitating further research on language generation, which requires extreme paraphrasing and coping with long research articles. We further improve the quality of the press releases using co-training with scientific abstracts of sources or partitioned press releases. Finally, we apply evaluation measures beyond ROUGE and we demonstrate improved performance for our method over strong baselines, which we further confirm by quantitative and qualitative evaluation.}, number={14}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Dangovski, Rumen and Shen, Michelle and Byrd, Dawson and Jing, Li and Tsvetkova, Desislava and Nakov, Preslav and Soljačić, Marin}, year={2021}, month={May}, pages={12728-12737} }