arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.12949cs.CLcs.AI
收藏

语义匹配知识图谱嵌入的对偶诱导正则化方法

Duality-Induced Regularizer for Semantic Matching Knowledge Graph Embeddings

University of Science and Technology of China(中国科学技术大学);Hefei Comprehensive National Science Center(合肥综合性国家科学中心);Texas A&M University(德克萨斯农工大学)

Jie Wang, Zhanqiu Zhang, Zhihao Shi, Jianyu Cai, Shuiwang Ji, Feng Wu

摘要:

语义匹配模型--假设具有相似语义的实体具有相似的嵌入--在知识图谱嵌入(KGE)中显示出强大的功能。现有的语义匹配模型多采用嵌入空间的内积来度量静态和时态知识图谱中三元组和四元组的可扩展性。然而,与另一个向量具有相同内积的向量仍然可以彼此正交,这意味着具有相似语义的实体可能具有不同的嵌入。内积的这种性质极大地限制了语义匹配模型的性能。为了解决这一挑战,我们提出了一种新的正则化器-即Duality-induced Regularizer(DURA)-它有效地鼓励具有相似语义的实体具有相似的嵌入。DURA的主要新颖性是基于这样的观察,即对于现有的语义匹配KGE模型(原始),通常存在另一个与之密切相关的基于距离的KGE模型(对偶),这可以用作实体嵌入的有效约束。实验表明,DURA一致和显着提高了最先进的静态和时间知识图谱基准的语义匹配模型的性能。

英文摘要:

Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE). Many existing semantic matching models use inner products in embedding spaces to measure the plausibility of triples and quadruples in static and temporal knowledge graphs. However, vectors that have the same inner products with another vector can still be orthogonal to each other, which implies that entities with similar semantics may have dissimilar embeddings. This property of inner products significantly limits the performance of semantic matching models. To address this challenge, we propose a novel regularizer -- namely, DUality-induced RegulArizer (DURA) -- which effectively encourages the entities with similar semantics to have similar embeddings. The major novelty of DURA is based on the observation that, for an existing semantic matching KGE model (primal), there is often another distance based KGE model (dual) closely associated with it, which can be used as effective constraints for entity embeddings. Experiments demonstrate that DURA consistently and significantly improves the performance of state-of-the-art semantic matching models on both static and temporal knowledge graph benchmarks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑