Accepted paper at ACL 2022 Workshop SPNLP 2022
TempCaps: A Capsule Network-based Embedding Model for Temporal Knowledge Graph Completion
04.04.2022
Authors
Guirong Fu, Zhao Meng, Yunpu Ma, Zhen Han, Zifeng Ding, Matthias Schubert, Roger Wattenhofer
The 6th ACL Workshop on Structured Prediction for NLP (SPNLP 2022)
at the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022),
22–27 May 2022, Dublin, Ireland
Abstract
TempCaps models temporal knowledge graphs by introducing a novel dynamic routing aggregator inspired by Capsule Networks. Specifically, TempCaps builds entity embeddings by dynamically routing retrieved temporal relation and neighbor information.