arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.00327cs.AI
收藏

从历史中寻找,从未来中推理:时间知识图谱的两阶段推理

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs

University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司)

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

摘要:

时态知识图谱(TKG)已经被开发并应用于许多不同的领域。对TKG进行推理,预测未来潜在的事实(事件),给现有的模型带来了巨大的挑战。当面临预测任务时,人类通常搜索有用的历史信息(即,线索)在他们的记忆,然后对未来的原因精心。受此机制的启发,我们提出了ClusteR预测未来的事实在两个阶段的方式,线索搜索和时间推理,相应的。具体而言,在线索搜索阶段,ClusteR通过强化学习(RL)学习束搜索策略,以从历史事实中归纳出多个线索。在时间推理阶段,采用基于图卷积网络的序列方法从线索中推理答案。在四个数据集上的实验表明,与最先进的方法相比,ClusteR的实质性优势。此外,ClusteR发现的线索进一步为结果提供了可解释性。

英文摘要:

Temporal Knowledge Graphs (TKGs) have been developed and used in many different areas. Reasoning on TKGs that predicts potential facts (events) in the future brings great challenges to existing models. When facing a prediction task, human beings usually search useful historical information (i.e., clues) in their memories and then reason for future meticulously. Inspired by this mechanism, we propose CluSTeR to predict future facts in a two-stage manner, Clue Searching and Temporal Reasoning, accordingly. Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts. At the temporal reasoning stage, it adopts a graph convolution network based sequence method to deduce answers from clues. Experiments on four datasets demonstrate the substantial advantages of CluSTeR compared with the state-of-the-art methods. Moreover, the clues found by CluSTeR further provide interpretability for the results.

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。

↑