arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.13035cs.CLcs.LG
收藏

SASA: 一种带有分离注意力机制的语义感知对比学习框架用于三元组分类

SASA: Semantic-Aware Contrastive Learning Framework with Separated Attention for Triple Classification

organization= Aerospace Science \& Industry Defense Technology Research;Test Center , addressline= Yongding Road , city= Beijing , postcode= 100039 , country= China

Xu Xiaodan, Hu Xiaolin

AI总结:

SASA通过分离注意力机制和语义感知对比学习提升三元组分类的准确性,实现了在两个基准数据集上的性能提升。

摘要:

知识图谱(KGs)常常面临不可靠的知识,这限制了它们的实用性。三元组分类(TC)旨在确定来自KGs的三元组的有效性。最近,基于文本的方法通过自然语言描述学习实体和关系表示,显著提高了TC模型的泛化能力,并在性能上设定了新的基准。然而,仍然存在两个关键挑战。首先,现有方法常常忽略了不同KG组件之间的有效语义交互。其次,大多数方法采用单一二元分类训练目标,导致语义表示学习不足。为了解决这些挑战,我们提出了SASA,一种新的框架,旨在通过分离注意力机制和语义感知对比学习(CL)来增强TC模型。具体来说,我们首先提出分离注意力机制,将三元组编码为解耦的上下文表示,然后通过更有效的交互方式融合它们。然后,我们引入语义感知的分层CL作为辅助训练目标,以指导模型在提高判别能力并实现充分的语义学习方面取得进展,考虑了局部和全局层面的CL。在两个基准数据集上的实验结果表明,SASA显著优于最先进的方法。在准确性方面,我们在FB15k-237上提高了5.9%,在YAGO3-10上提高了3.4%。

英文摘要:

Knowledge Graphs~(KGs) often suffer from unreliable knowledge, which restricts their utility. Triple Classification~(TC) aims to determine the validity of triples from KGs. Recently, text-based methods learn entity and relation representations from natural language descriptions, significantly improving the generalization capabilities of TC models and setting new benchmarks in performance. However, there are still two critical challenges. First, existing methods often ignore the effective semantic interaction among different KG components. Second, most approaches adopt single binary classification training objective, leading to insufficient semantic representation learning. To address these challenges, we propose \textbf{SASA}, a novel framework designed to enhance TC models via separated attention mechanism and semantic-aware contrastive learning~(CL). Specifically, we first propose separated attention mechanism to encode triples into decoupled contextual representations and then fuse them through a more effective interactive way. Then, we introduce semantic-aware hierarchical CL as auxiliary training objective to guide models in improving their discriminative capabilities and achieving sufficient semantic learning, considering both local level and global level CL. Experimental results across two benchmark datasets demonstrate that SASA significantly outperforms state-of-the-art methods. In terms of accuracy, we advance the state-of-the-art by +5.9\% on FB15k-237 and +3.4\% on YAGO3-10.

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。

↑