解决时间知识图谱问答中多步推理难题，提升复杂时序查询准确率。
SABET-QA: Temporal Knowledge Graph Question Answering
- 通过双向实体-时间评分与槽位感知上下文模块，迭代优化推理状态
- 在多步时序问答数据集上显著优于现有方法，尤其在复杂查询上提升明显
- 适合需要精准时序推理的智能问答系统开发者参考
面向时间知识图谱的问答任务需对时敏事实进行推理，但现有基于嵌入的方法因单次遍历推理流程，在多步查询上表现不佳。我们提出SABET-QA框架，通过双向实体-时间评分机制与槽位感知上下文模块，实现跨多跳的推理状态迭代优化。可微的工作记忆支持渐进式假设修正，辅助时间边界提供粗粒度监督。在CronQuestions、Complex-CronQuestions、MultiTQ和TimeQuestions数据集上的实验表明，该方法持续优于强基线，尤其在复杂多步时序查询上表现突出。
原文摘要 · Abstract (English)
Question Answering over Temporal Knowledge Graphs (TKGQA) requires reasoning over time-sensitive facts, yet existing embedding-based methods struggle with multi-step queries due to single-pass reasoning pipelines. We propose SABET-QA, a framework that iteratively refines reasoning states across multiple hops via a bidirectional entity-temporal scoring mechanism and a slot-aware contextualization module that aligns question semantics with temporal KG embeddings. A differentiable working memory enables progressive hypothesis refinement, while auxiliary temporal boundaries serve as coarse supervision when available. Experiments on CronQuestions, Complex-CronQuestions, MultiTQ, and TimeQuestions demonstrate consistent improvements over strong baselines, particularly on complex multi-step temporal queries.
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。