Li Bei, Li Changbiao, Sun Jianwei, Zeng Xu, Chen Xiaofan, Zheng Jing
Department of Biomedical Informatics, School of Life Science, Central South University, Changsha, Hunan, China.
Shenzhen Health Development Research and Data Management Center, Shenzhen, Guangdong, China.
PLoS One. 2025 May 29;20(5):e0325082. doi: 10.1371/journal.pone.0325082. eCollection 2025.
The field of information extraction (IE) is currently exploring more versatile and efficient methods for minimization of reliance on extensive annotated datasets and integration of knowledge across tasks and domains.
We aim to evaluate and refine the application of the universal IE (UIE) technology in the field of Chinese medical expertise in terms of processing accuracy and efficiency.
Our model integrates ontology modeling, web scraping, UIE, fine-tuning strategies, and graph databases, thereby covering knowledge modeling, extraction, and storage techniques. The Enhanced Representation through Knowledge Integration-UIE (ERNIE-UIE) model is fine-tuned and optimized using a small amount of annotated data. A medical knowledge graph is then constructed, followed by validating the graph and conducting knowledge mining on the data stored within it.
Incorporating the characteristics of whole-course management, we implemented a comprehensive medical knowledge graph-construction model and methodology. Entities and relationships were jointly extracted using the pretrained language model, resulting in 8,525 entity data points and 9,522 triple data points. The accuracy of the knowledge graph was verified using graph algorithms.
We optimized the construction process of a Chinese medical knowledge graph with minimal annotated data by utilizing a generative extraction paradigm, validating the graph's efficacy and achieving commendable results. This approach addresses the challenge of insufficient annotated training corpora in low-resource knowledge graph construction, thereby contributing to cost savings in the development of knowledge graphs.
信息提取（IE）领域目前正在探索更通用、高效的方法，以尽量减少对大量标注数据集的依赖，并实现跨任务和领域的知识整合。
我们旨在从处理准确性和效率方面评估和优化通用信息提取（UIE）技术在中国医学专业领域的应用。
我们的模型整合了本体建模、网络爬虫、UIE、微调策略和图数据库，从而涵盖了知识建模、提取和存储技术。通过知识整合增强表示-通用信息提取（ERNIE-UIE）模型使用少量标注数据进行微调与优化。随后构建医学知识图谱，接着对图谱进行验证并对存储在其中的数据进行知识挖掘。
结合全程管理的特点，我们实现了一个全面的医学知识图谱构建模型和方法。利用预训练语言模型联合提取实体和关系，得到8525个实体数据点和9522个三元组数据点。使用图算法验证了知识图谱的准确性。
我们利用生成式提取范式，以最少的标注数据优化了中医知识图谱的构建过程，验证了图谱的有效性并取得了值得称赞的结果。该方法解决了低资源知识图谱构建中标注训练语料不足的挑战，从而有助于节省知识图谱开发成本。
