Selective Temporal Knowledge Graph Reasoning

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng

Abstract
Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently. TKG reasoning aims to predict future facts based on given historical ones. However, existing TKG reasoning models are unable to abstain from predictions they are uncertain, which will inevitably bring risks in real-world applications. Thus, in this paper, we propose an abstention mechanism for TKG reasoning, which helps the existing models make selective, instead of indiscriminate, predictions. Specifically, we develop a confidence estimator, called Confidence Estimator with History (CEHis), to enable the existing TKG reasoning models to first estimate their confidence in making predictions, and then abstain from those with low confidence. To do so, CEHis takes two kinds of information into consideration, namely, the certainty of the current prediction and the accuracy of historical predictions. Experiments with representative TKG reasoning models on two benchmark datasets demonstrate the effectiveness of the proposed CEHis.
Anthology ID:
2024.lrec-main.1268
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
14555–14566
Language:
URL:
https://aclanthology.org/2024.lrec-main.1268
DOI:
Bibkey:
Cite (ACL):
Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, and Xueqi Cheng. 2024. Selective Temporal Knowledge Graph Reasoning. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 14555–14566, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Selective Temporal Knowledge Graph Reasoning (Hou et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.1268.pdf
PDF Search