Encoding Temporal Information for Time-Aware Link Prediction

Tingsong Jiang1, Tianyu Liu2, Tao Ge3, Lei Sha4, Sujian Li4, Baobao Chang4, Zhifang Sui5
1Institute of Computational Linguistics,Peking University, 2PKU, 3Key Laboratory of Computational Linguistics, Peking University, 4Peking University, 5


Abstract

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 results show that our method outperforms other baselines on the two tasks consistently.