通用NLP嵌入能否捕获本体论推理？
Do General NLP Embeddings Capture Ontological Reasoning?
浏览论文内容
中文总结 AI 辅助
该研究提出AVA框架评估通用NLP嵌入的本体推理能力，发现现有模型在逻辑敏感三元组任务中表现差，微调后难迁移至语义网任务，凸显语言表示与本体理解的差距。
中文摘要 AI 辅助
通用NLP嵌入模型在语言任务上表现良好，但其捕获符号本体结构的能力仍不明确。我们推出AVA，一个用于评估嵌入是否区分本体和知识图谱中逻辑敏感关系语义的系统框架。AVA包含171007个对比三元组，这些三元组源自163个异构本体，通过层级反转、关系替换和不相交性注入生成。每个三元组包含一个本体陈述、一个语义等价的释义，以及一个具有矛盾关系意义的逻辑敏感难负例。我们评估了25多个最先进的嵌入模型，发现存在显著局限：最佳模型仅达到0.739的三元组准确率，而难负例准确率降至0.135。微调大幅提升了区分度，但向下游语义网任务（包括分类发现和本体对齐）的迁移效果不佳。进一步分析表明，改进部分源于特定扰动的模式识别，而非稳健的本体理解。这些发现揭示了语言表示学习与本体级区分之间存在持续的差距，挑战了“NLP基准性能强即等同于语义网能力强”的假设。
英文摘要
General-purpose NLP embedding models perform well on linguistic tasks, but their ability to capture symbolic ontological structure remains unclear. We introduce AVA, a systematic framework for evaluating whether embeddings distinguish logic-sensitive relational semantics in ontologies and knowledge graphs. AVA comprises 171,007 contrastive triplets derived from 163 heterogeneous ontologies using hierarchy inversion, relation substitution, and disjointness injection. Each triplet contains an ontology statement, a semantically equivalent paraphrase, and a logic-sensitive hard negative with contradictory relational meaning. We evaluate more than 25 state-of-the-art embedding models and find substantial limitations: the best model achieves only 0.739 triplet accuracy, while hard negative accuracy falls to 0.135. Fine-tuning improves discrimination by a large margin but transfers poorly to downstream Semantic Web tasks, including taxonomy discovery and ontology alignment. Further analysis suggests that improvements stem partly from perturbation-specific pattern recognition rather than robust ontological understanding. These findings reveal a persistent gap between linguistic representation learning and ontology-level discrimination, challenging the assumption that strong NLP benchmark performance translates to Semantic Web competence.
发表机构
- TIB Leibniz Information Centre for Science and Technology（TIB莱布尼茨科学与技术信息中心）
- Leibniz University of Hannover（汉诺威莱布尼茨大学）
机构由 AI 辅助整理，请以论文原文为准。
