COVID-19 文献知识图谱构建与药物重定位报告生成
计算与语言
2025-06-11 v6 人工智能
摘要
为抗击 COVID-19，临床医生和科学家都需要消化科学文献中大量相关的生物医学知识，以理解疾病机制及相关生物学功能。我们开发了一个新颖且全面的知识发现框架 COVID-KG，用于从科学文献中提取细粒度的多媒体知识元素（实体及其视觉化学结构、关系和事件）。然后我们以药物重定位为案例研究，利用所构建的多媒体知识图谱（KGs）进行问答和报告生成。我们的框架还提供详细的上下文句子、子图以及知识子图作为证据。
引用
@article{arxiv.2007.00576,
title = {COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation},
author = {Qingyun Wang and Manling Li and Xuan Wang and Nikolaus Parulian and Guangxing Han and Jiawei Ma and Jingxuan Tu and Ying Lin and Haoran Zhang and Weili Liu and Aabhas Chauhan and Yingjun Guan and Bangzheng Li and Ruisong Li and Xiangchen Song and Yi R. Fung and Heng Ji and Jiawei Han and Shih-Fu Chang and James Pustejovsky and Jasmine Rah and David Liem and Ahmed Elsayed and Martha Palmer and Clare Voss and Cynthia Schneider and Boyan Onyshkevych},
journal= {arXiv preprint arXiv:2007.00576},
year = {2025}
}
备注
12 pages, Accepted by Proceedings of 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics System Demonstrations, for resources see http://blender.cs.illinois.edu/covid19/, for video see http://159.89.180.81/demo/covid/Covid-KG_DemoVideo.mp4, for slides see https://eaglew.github.io/files/Covid-KG_DemoVideo_with_ethics.pdf