{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/data-driven-summarization-of-scientific","title":"Data-driven Summarization of Scientific Articles","arxiv_id":"1804.08875","date":"2018-04-24","proceeding":null,"authors":["Nikola I. Nikolov","Michael Pfeiffer","Richard H. R. Hahnloser"],"abstract":"Data-driven approaches to sequence-to-sequence modelling have been\nsuccessfully applied to short text summarization of news articles. Such models\nare typically trained on input-summary pairs consisting of only a single or a\nfew sentences, partially due to limited availability of multi-sentence training\ndata. Here, we propose to use scientific articles as a new milestone for text\nsummarization: large-scale training data come almost for free with two types of\nhigh-quality summaries at different levels - the title and the abstract. We\ngenerate two novel multi-sentence summarization datasets from scientific\narticles and test the suitability of a wide range of existing extractive and\nabstractive neural network-based summarization approaches. Our analysis\ndemonstrates that scientific papers are suitable for data-driven text\nsummarization. Our results could serve as valuable benchmarks for scaling\nsequence-to-sequence models to very long sequences.","url_abs":"http://arxiv.org/abs/1804.08875v1","url_pdf":"http://arxiv.org/pdf/1804.08875v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"data-driven-summarization-of-scientific","repo_url":"https://github.com/ninikolov/data-driven-summarization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"data-driven-summarization-of-scientific","repo_url":"https://github.com/Santosh-Gupta/Arxiv-Manatee","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"data-driven-summarization-of-scientific","repo_url":"https://github.com/jananiarunachalam/Research-Paper-Summarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-summarization","task_name":"Sentence Summarization"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.08875","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}