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 (i.e., 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 (e.g. 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.- Anthology ID:
- 2023.emnlp-main.76
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1186–1202
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.76
- DOI:
- 10.18653/v1/2023.emnlp-main.76
- Cite (ACL):
- Ronald Cardenas, Bingsheng Yao, Dakuo Wang, and Yufang Hou. 2023. ‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1186–1202, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- ‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalism (Cardenas et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.76.pdf