Scholarlink

<p>The digitization of Chinese Cultural Heritage (CCH) facilitates the study of its long-term evolution, driving growing interest in Temporal Knowledge Graph Reasoning (TKGR). However, modeling the complex temporal dependencies remains a major challenge, particularly in long-cycle domains with rich contextual semantics like CCH. To this end, we propose the <b>D</b>ual <b>T</b>emporal <b>D</b>ependency <b>M</b>odel (DTDM), a novel TKGR framework that decouples and jointly models two temporal dependencies: (1) a temporal cross-relation evolution module, which uses attention mechanisms to capture dynamic interactions among relations; and (2) a temporal convolution module, which combines gated recurrent unit to capture the long-range evolution and parallel convolutions to enhance entity representations. We constructed CCH-Ceramics, the first TKG dataset focused on Chinese ceramics. Experimental results on three benchmarks demonstrate that DTDM significantly outperforms all baselines, achieving a 4.13% absolute improvement in performance on entity prediction on CCH-Ceramics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Modeling dual temporal dependencies for temporal knowledge graph reasoning on Chinese cultural heritage

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月3日

查看全文
  • Yan Wang,
  • Pengju Xu,
  • Haiying Zhao,
  • Kun Xu

摘要

The digitization of Chinese Cultural Heritage (CCH) facilitates the study of its long-term evolution, driving growing interest in Temporal Knowledge Graph Reasoning (TKGR). However, modeling the complex temporal dependencies remains a major challenge, particularly in long-cycle domains with rich contextual semantics like CCH. To this end, we propose the Dual Temporal Dependency Model (DTDM), a novel TKGR framework that decouples and jointly models two temporal dependencies: (1) a temporal cross-relation evolution module, which uses attention mechanisms to capture dynamic interactions among relations; and (2) a temporal convolution module, which combines gated recurrent unit to capture the long-range evolution and parallel convolutions to enhance entity representations. We constructed CCH-Ceramics, the first TKG dataset focused on Chinese ceramics. Experimental results on three benchmarks demonstrate that DTDM significantly outperforms all baselines, achieving a 4.13% absolute improvement in performance on entity prediction on CCH-Ceramics.