用高斯盒嵌入提升分类体系自动扩展，解决语义模糊与层级关系难题。
TaxoBell: Gaussian Box Embeddings for Self-Supervised Taxonomy Expansion
- 将盒子几何转化为多元高斯分布，用均值和协方差表示语义位置与不确定性
- 在五个数据集上相比主流方法提升19% MRR和约25% Recall@k
- 适合需要处理模糊概念和层级推理的结构化知识构建任务
分类体系是跨领域结构化知识表示的核心，支持电商与语义搜索等应用。然而人工扩展分类体系成本高、速度慢。现有方法依赖点式向量嵌入，仅能建模对称相似性，难以捕捉分类体系中固有的非对称关系。盒嵌入虽可建模包含与不相交关系，但存在三大问题：(i) 交界处梯度不稳定，(ii) 缺乏语义不确定性建模能力，(iii) 难以表达多义性或模糊性。我们提出TaxoBell，一种高斯盒嵌入框架，将盒几何映射为多元高斯分布，其中均值编码语义位置，协方差编码不确定性。基于能量的优化实现稳定训练，有效建模模糊概念，并支持可解释的层次推理。在五个基准数据集上的实验表明，TaxoBell显著优于八种前沿基线方法，MRR提升19%，Recall@k提升约25%。误差分析与消融研究进一步揭示了其优势与局限。
原文摘要 · Abstract (English)
Taxonomies form the backbone of structured knowledge representation across diverse domains, enabling applications such as e-commerce and semantic search. Yet, manual taxonomy expansion is labor-intensive and slow. Existing methods rely on point-based vector embeddings, which model symmetric similarity and thus struggle with the asymmetric relationships that are fundamental to taxonomies. Box embeddings offer a promising alternative by enabling containment and disjointness, but they face key issues: (i) unstable gradients at the intersection boundaries, (ii) no notion of semantic uncertainty, and (iii) limited capacity to represent polysemy or ambiguity. We address these shortcomings with TaxoBell, a Gaussian box embedding framework that translates between box geometries and multivariate Gaussian distributions, where means encode semantic location and covariances encode uncertainty. Energy-based optimization yields stable optimization, robust modeling of ambiguous concepts, and interpretable hierarchical reasoning. Extensive experiments on five benchmark datasets demonstrate that TaxoBell significantly outperforms eight state-of-the-art taxonomy expansion baselines by 19% in MRR and around 25% in Recall@k. We further demonstrate the advantages and pitfalls of TaxoBell with error analysis and ablation studies.
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。