用邻居信息增强BERT，更准地补全知识图谱中的缺失关系。
A Contextualized BERT model for Knowledge Graph Completion
- 基于上下文构建BERT模型，利用邻近实体和关系信息预测尾实体。
- 在FB15k-237和WN18RR上分别提升Hit@1达5.3%和4.88%。
- 无需实体描述和负样本采样，计算更高效，适合大规模图谱补全。
知识图谱（KG）是跨领域结构化信息的重要载体，支持语义搜索、推荐系统等任务。但许多实体或关系缺失，影响其完整性。知识图谱补全（KGC）旨在预测缺失的头尾实体或关系，提升图谱价值。传统方法如TransE、ComplEx仅能预测尾实体，难以处理未见实体；基于文本的方法虽引入语义信息，却存在计算开销大、语义不一致和数据不平衡等问题。近期大模型方法虽有改进，但仍忽略上下文信息且依赖实体描述。本文提出一种上下文感知的BERT模型，通过利用邻接实体与关系的上下文信息进行尾实体预测，无需实体描述和负三元组采样，显著降低计算成本。实验表明，该模型在标准数据集上优于现有方法，在FB15k-237和WN18RR上分别实现Hit@1提升5.3%和4.88%，树立了新基准。
原文摘要 · Abstract (English)
Knowledge graphs (KGs) are valuable for representing structured, interconnected information across domains, enabling tasks like semantic search, recommendation systems and inference. A pertinent challenge with KGs, however, is that many entities (i.e., heads, tails) or relationships are unknown. Knowledge Graph Completion (KGC) addresses this by predicting these missing nodes or links, enhancing the graph's informational depth and utility. Traditional methods like TransE and ComplEx predict tail entities but struggle with unseen entities. Textual-based models leverage additional semantics but come with high computational costs, semantic inconsistencies, and data imbalance issues. Recent LLM-based models show improvement but overlook contextual information and rely heavily on entity descriptions. In this study, we introduce a contextualized BERT model for KGC that overcomes these limitations by utilizing the contextual information from neighbouring entities and relationships to predict tail entities. Our model eliminates the need for entity descriptions and negative triplet sampling, reducing computational demands while improving performance. Our model outperforms state-of-the-art methods on standard datasets, improving Hit@1 by 5.3% and 4.88% on FB15k-237 and WN18RR respectively, setting a new benchmark in KGC.
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。