提出可扩展的科学文献知识图谱生成框架，解决实体识别与层次关系建模难题。
HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
- 分两阶段构建：先用OSD与多尺度注意力识别长实体，再通过层次消息传递抽取关系
- 在跨域测试中实体识别提升8.08%，关系抽取提升5.99%，零样本下关系抽取增益达26.2%
- 首次将层次抽象建模为欧氏空间连续属性，更适合通用模型部署
自动化知识图谱（KG）构建对应对快速增长的科学文献至关重要。现有方法难以识别长复合实体，泛化能力差，且忽略科学知识的层级结构。通用大模型虽灵活但计算成本高，任务精度不稳，导致现有知识图谱浅层且不一致。本文提出两阶段可扩展的零样本科学文献知识图谱构建框架。第一阶段Z-NERD引入正交语义分解（OSD），通过分离文本中的语义“转折点”实现领域无关实体识别；并设计多尺度TCQK注意力机制，利用n-gram感知头捕捉连贯的多词实体。第二阶段HGNet采用层次感知消息传递进行关系抽取，显式建模父、子及同级关系。为保证全局一致性，提出两种互补目标：可微分层次损失抑制环路和捷径边，连续抽象场（CAF）损失将抽象层级嵌入可学习的欧氏轴上。这是首个在标准欧氏空间中形式化层次抽象为连续属性的方法，替代了复杂的双曲方法。我们发布SPHERE（https://github.com/basiralab/SPHERE）——一个多领域层次关系抽取基准。该框架在SciERC、SciER和SPHERE上均达到新最佳性能，跨域测试中实体识别提升8.08%，关系抽取提升5.99%；零样本设置下，实体识别增益达10.76%，关系抽取增益高达26.2%。
原文摘要 · Abstract (English)
Automated knowledge graph (KG) construction is essential for navigating the rapidly expanding body of scientific literature. However, existing approaches struggle to recognize long multi-word entities, often fail to generalize across domains, and typically overlook the hierarchical nature of scientific knowledge. While general-purpose large language models (LLMs) offer adaptability, they are computationally expensive and yield inconsistent accuracy on specialized tasks. As a result, current KGs are shallow and inconsistent, limiting their utility for exploration and synthesis. We propose a two-stage framework for scalable, zero-shot scientific KG construction. The first stage, Z-NERD, introduces (i) Orthogonal Semantic Decomposition (OSD), which promotes domain-agnostic entity recognition by isolating semantic "turns" in text, and (ii) a Multi-Scale TCQK attention mechanism that captures coherent multi-word entities through n-gram-aware attention heads. The second stage, HGNet, performs relation extraction with hierarchy-aware message passing, explicitly modeling parent, child, and peer relations. To enforce global consistency, we introduce two complementary objectives: a Differentiable Hierarchy Loss to discourage cycles and shortcut edges, and a Continuum Abstraction Field (CAF) Loss that embeds abstraction levels along a learnable axis in Euclidean space. This is the first approach to formalize hierarchical abstraction as a continuous property within standard Euclidean embeddings, offering a simpler alternative to hyperbolic methods. We release SPHERE (https://github.com/basiralab/SPHERE), a multi-domain benchmark for hierarchical relation extraction. Our framework establishes a new state of the art on SciERC, SciER, and SPHERE, improving NER by 8.08% and RE by 5.99% on out-of-distribution tests. In zero-shot settings, gains reach 10.76% for NER and 26.2% for RE.
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。