entity-normalization 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
DoTAT 是一款基于web、面向领域的通用文本标注工具，支持大规模实体标注、关系标注、事件标注、文本分类、基于字典匹配和正则匹配的自动标注以及用于实现归一化的标准名标注，同时也支持迭代标注、嵌套实体标注和嵌套事件标注。标注规范可自定义且同类型任务中可“一次创建多次复用”。通过分级实体集合扩大了实体类型的规模，并设计了全新高效的标注方式，提升了用户体验和标注效率。此外，本工具增加了审核环节，可对多人的标注结果进行一致性检验、自动合并和手动调整，提高了标注结果的准确率。
walks mapping graphs running boomer
Entity recognition (organization, location, items, serial numbers) and entity normalization (organization, names) with character-level Convolutional neural network
SkeinRank — Domain Language Control Plane for enterprise search, RAG, and AI-agent workflows.
Comparative analysis of NLP neural methods for the entity normalization task in the biological field.
Implementation of a BERT model to normalize biological entities from the Bacteria Biotope 4 corpus.
Messy country names → ISO 3166 codes, with a calibrated "I don't know". A 75 MB open model for registers and forms: CPU or browser, certified error rates.