{"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/paperrobot-incremental-draft-generation-of","title":"PaperRobot: Incremental Draft Generation of Scientific Ideas","arxiv_id":"1905.07870","date":"2019-05-20","proceeding":"ACL 2019 7","authors":["Qingyun Wang","Lifu Huang","Zhiying Jiang","Kevin Knight","Heng Ji","Mohit Bansal","Yi Luan"],"abstract":"We present a PaperRobot who performs as an automatic research assistant by (1) conducting deep understanding of a large collection of human-written papers in a target domain and constructing comprehensive background knowledge graphs (KGs); (2) creating new ideas by predicting links from the background KGs, by combining graph attention and contextual text attention; (3) incrementally writing some key elements of a new paper based on memory-attention networks: from the input title along with predicted related entities to generate a paper abstract, from the abstract to generate conclusion and future work, and finally from future work to generate a title for a follow-on paper. Turing Tests, where a biomedical domain expert is asked to compare a system output and a human-authored string, show PaperRobot generated abstracts, conclusion and future work sections, and new titles are chosen over human-written ones up to 30%, 24% and 12% of the time, respectively.","url_abs":"https://arxiv.org/abs/1905.07870v4","url_pdf":"https://arxiv.org/pdf/1905.07870v4.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":"paperrobot-incremental-draft-generation-of","repo_url":"https://github.com/EagleW/PaperRobot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"paperrobot-incremental-draft-generation-of","repo_url":"https://github.com/thorMax/AIPaperWriter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"paper-generation","task_name":"Paper generation"},{"task_slug":"paper-generation-conclusion-to-title","task_name":"Paper generation (Conclusion-to-title)"},{"task_slug":"paper-generation-title-to-abstract","task_name":"Paper generation (Title-to-abstract)"},{"task_slug":"paper-generation-abstract-to-conclusion","task_name":"Paper generation (abstract-to-conclusion)"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"memory-network","method_name":"Memory Network"},{"method_slug":"pointer-net","method_name":"Pointer Network"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"pubmed-paper-reading-dataset","name":"PubMed Paper Reading Dataset","full_name":""},{"slug":"pubmed-term-abstract-conclusion-title-dataset","name":"PubMed Term, Abstract, Conclusion, Title Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.07870","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}