Encoding Temporal Information for Time-Aware Link Prediction
Encoding Temporal Information for Time-Aware Link Prediction
复制标题
DOI：
10.18653/v1/d16-1260
复制
发表时间：
2016-11
影响因子：
5
通讯作者：
Tingsong Jiang;Tianyu Liu;Tao Ge;Lei Sha;Sujian Li;Baobao Chang;Zhifang Sui
中科院分区：
文献类型：
--
作者：
Tingsong Jiang;Tianyu Liu;Tao Ge;Lei Sha;Sujian Li;Baobao Chang;Zhifang Sui
现有的知识库（KB）嵌入方法大多只学习时间未知的事实三元组，而忽略了知识库中的时间信息。在本文中，我们提出了一种新的时间感知的知识库嵌入方法，利用事实的发生时间。具体来说，我们使用时序约束来建模时间敏感关系之间的转换，并强制嵌入在时间上一致且更准确。我们在链接预测和三重分类两个任务中实证评估了我们的方法。实验结果表明，我们的方法优于其他基线上的两个任务一致。
Most existing knowledge base (KB) embedding methods solely learn from time-unknown fact triples but neglect the temporal information in the knowledge base. In this paper, we propose a novel time-aware KB embedding approach taking advantage of the happening time of facts. Specifically, we use temporal order constraints to model transformation between time-sensitive relations and enforce the embeddings to be temporally consistent and more accurate. We empirically evaluate our approach in two tasks of link prediction and triple classification. Experimental re-sults show that our method outperforms other baselines on the two tasks consistently.