Automatic generation of reviews of scientific papers
National Research University Higher School of Economics（国家研究型高等经济学院）；Université de Lorraine（洛林大学）；Sechenov Institute of Evolutionary Physiology and Biochemistry RAS（俄罗斯科学院谢切诺夫进化生理学和生物化学研究所）；Saint Petersburg State University（圣彼得堡国立大学）；JetBrains Research（JetBrains研究院）
Anna Nikiforovskaya, Nikolai Kapralov, Anna Vlasova, Oleg Shpynov, Aleksei Shpilman
With an ever-increasing number of scientific papers published each year, it becomes more difficult for researchers to explore a field that they are not closely familiar with already. This greatly inhibits the potential for cross-disciplinary research. A traditional introduction into an area may come in the form of a review paper. However, not all areas and sub-areas have a current review. In this paper, we present a method for the automatic generation of a review paper corresponding to a user-defined query. This method consists of two main parts. The first part identifies key papers in the area by their bibliometric parameters, such as a graph of co-citations. The second stage uses a BERT based architecture that we train on existing reviews for extractive summarization of these key papers. We describe the general pipeline of our method and some implementation details and present both automatic and expert evaluations on the PubMed dataset.
ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review
ETH Zürich, IVT & Agentic Systems Lab (ASL)（苏黎世联邦理工学院，信息与通信技术研究所及代理系统实验室）；European Commission, Joint Research Centre（欧洲委员会，联合研究中心）；University of Konstanz（康斯坦茨大学）；Ideas Forward
AutoKE: An automatic knowledge embedding framework for scientific machine learning
Peking University（北京大学）；Eastern Institute for Advanced Study, Yongriver Institute of Technology（甬江理工大学东方理工高等研究院）；Southern University of Science and Technology（南方科技大学）；Peng Cheng Laboratory（鹏城实验室）
