Learning Sequence Encoders for Temporal Knowledge Graph Completion

Alberto García-Durán, Sebastijan Dumančić, Mathias Niepert


Abstract
Research on link prediction in knowledge graphs has mainly focused on static multi-relational data. In this work we consider temporal knowledge graphs where relations between entities may only hold for a time interval or a specific point in time. In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations. To incorporate temporal information, we utilize recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods. The proposed approach is shown to be robust to common challenges in real-world KGs: the sparsity and heterogeneity of temporal expressions. Experiments show the benefits of our approach on four temporal KGs. The data sets are available under a permissive BSD-3 license.
Anthology ID:
D18-1516
Volume:
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Month:
October-November
Year:
2018
Address:
Brussels, Belgium
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
4816–4821
Language:
URL:
https://aclanthology.org/D18-1516
DOI:
10.18653/v1/D18-1516
Bibkey:
Cite (ACL):
Alberto García-Durán, Sebastijan Dumančić, and Mathias Niepert. 2018. Learning Sequence Encoders for Temporal Knowledge Graph Completion. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4816–4821, Brussels, Belgium. Association for Computational Linguistics.
Cite (Informal):
Learning Sequence Encoders for Temporal Knowledge Graph Completion (García-Durán et al., EMNLP 2018)
Copy Citation:
PDF:
https://aclanthology.org/D18-1516.pdf
Video:
 https://vimeo.com/306125393
Code
 nle-ml/mmkb +  additional community code
Data
ICEWS