Temporal Knowledge Graph Reasoning Based on N-tuple Modeling

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Saiping Guan, Yutao Zeng, Jiafeng Guo, Xueqi Cheng

Abstract
Reasoning over Temporal Knowledge Graphs (TKGs) that predicts temporal facts (e.g., events) in the future is crucial for many applications. The temporal facts in existing TKGs only contain their core entities (i.e., the entities playing core roles therein) and formulate them as quadruples, i.e., (subject entity, predicate, object entity, timestamp). This formulation oversimplifies temporal facts and inevitably causes information loss. Therefore, we propose to describe a temporal fact more accurately as an n-tuple, containing not only its predicate and core entities, but also its auxiliary entities, as well as the roles of all entities. By so doing, TKGs are augmented to N-tuple Temporal Knowledge Graphs (N-TKGs). To conduct reasoning over N-TKGs, we further propose N-tuple Evolutional Network (NE-Net). It recurrently learns the evolutional representations of entities and predicates in temporal facts at different timestamps in the history via modeling the relations among those entities and predicates. Based on the learned representations, reasoning tasks at future timestamps can be realized via task-specific decoders. Experiment results on two newly built datasets demonstrate the superiority of N-TKG and the effectiveness of NE-Net.
Anthology ID:
2023.findings-emnlp.77
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1090–1100
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.77
DOI:
10.18653/v1/2023.findings-emnlp.77
Bibkey:
Cite (ACL):
Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Saiping Guan, Yutao Zeng, Jiafeng Guo, and Xueqi Cheng. 2023. Temporal Knowledge Graph Reasoning Based on N-tuple Modeling. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1090–1100, Singapore. Association for Computational Linguistics.
Cite (Informal):
Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (Hou et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.77.pdf
PDF Search