从生物医学文献中挖掘叙事模式，助力精准发现药物关联。
Demonstrating Narrative Pattern Discovery from Biomedical Literature
- 基于图结构发现药物实体间的上下文关联模式。
- 通过专家访谈验证原型系统在真实场景中的有效性。
- 适合药学研究者快速发现潜在药物相互作用。
数字图书馆存储大量知识，需提供高效访问路径。例如德国药学专用信息服务PubPharm，为底层生物医学文献集合提供关键词搜索、化学结构检索及新型基于图的发现工作流，如列举或搜索不同药物实体间的相互作用。本文提出一种新搜索功能——叙事模式挖掘，帮助用户探索上下文相关的实体及其交互关系。我们通过与五位领域专家访谈，验证了原型系统的实用性。
原文摘要 · Abstract (English)
Digital libraries maintain extensive collections of knowledge and need to provide effective access paths for their users. For instance, PubPharm, the specialized information service for Pharmacy in Germany, provides and develops access paths to their underlying biomedical document collection. In brief, PubPharm supports traditional keyword-based search, search for chemical structures, as well as novel graph-based discovery workflows, e.g., listing or searching for interactions between different pharmaceutical entities. This paper introduces a new search functionality, called narrative pattern mining, allowing users to explore context-relevant entities and entity interactions. We performed interviews with five domain experts to verify the usefulness of our prototype.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。