Results 11 to 20 of about 8,113 (297)

Selective Temporal Knowledge Graph Reasoning [PDF]

Proceedings of the Language Resources and Evaluation Conference
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 ...
Zhongni Hou, Xiaolong Jin 0001, Zixuan Li 0001, Long Bai 0002, Jiafeng Guo, Xueqi Cheng   +5 more
openaire   +4 more sources

TempoQR: Temporal Question Reasoning over Knowledge Graphs [PDF]

Proceedings of the AAAI Conference on Artificial Intelligence, 2022
Knowledge Graph Question Answering (KGQA) involves retrieving facts from a Knowledge Graph (KG) using natural language queries. A KG is a curated set of facts consisting of entities linked by relations. Certain facts include also temporal information forming a Temporal KG (TKG).
Costas Mavromatis, Prasanna Lakkur Subramanyam, Vassilis N. Ioannidis, Adesoji Adeshina, Phillip Ryan Howard, Tetiana Grinberg, Nagib Hakim, George Karypis   +7 more
openaire   +3 more sources

Temporal Knowledge Graph Embedding and Reasoning [PDF]

, 2023
Knowledge Graphs (KGs) have emerged as an efficient way to organize and represent knowledge by storing the underlying relations between entities. Recently, a large amount of research works have been devoted to KG embeddings, aiming at mapping entities and relations in KGs to low-dimensional continuous vector spaces for fast reasoning.
Xu, Chengjin
openaire   +4 more sources

Chain-of-History Reasoning for Temporal Knowledge Graph Forecasting [PDF]

Findings of the Association for Computational Linguistics ACL 2024
Temporal Knowledge Graph (TKG) forecasting aims to predict future facts based on given histories. Most recent graph-based models excel at capturing structural information within TKGs but lack semantic comprehension abilities. Nowadays, with the surge of LLMs, the LLM-based TKG prediction model has emerged. However, the existing LLM-based model exhibits
Yuwei Xia, Ding Wang, Qiang Liu 0006, Liang Wang 0056, Shu Wu, Xiaoyu Zhang 0002   +5 more
openaire   +3 more sources

Causal Decoupling for Temporal Knowledge Graph Reasoning via Contrastive Learning and Adaptive Fusion [PDF]

Information
Temporal knowledge graphs (TKGs) are crucial for modeling evolving real-world facts and are widely applied in event forecasting and risk analysis. However, current TKG reasoning models struggle to separate causal signals from noisy observations, align ...
Siling Feng, Housheng Lu, Qian Liu, Peng Xu, Yujie Zheng, Bolin Chen, Mengxing Huang   +6 more
doaj   +2 more sources

Towards Representing Processes and Reasoning with Process Descriptions on the Web [PDF]

Transactions on Graph Data and Knowledge
We work towards a vocabulary to represent processes and temporal logic specifications as graph-structured data. Different fields use incompatible terminologies for describing essentially the same process-related concepts.
Harth, Andreas, Käfer, Tobias, Rula, Anisa, Calbimonte, Jean-Paul, Kamburjan, Eduard, Giese, Martin   +5 more
doaj   +3 more sources

DREAM: Adaptive Reinforcement Learning based on Attention Mechanism for Temporal Knowledge Graph Reasoning [PDF]

, 2023
Temporal knowledge graphs (TKGs) model the temporal evolution of events and have recently attracted increasing attention. Since TKGs are intrinsically incomplete, it is necessary to reason out missing elements.
Zheng, S, Chen, T, Chen, W, Zhao, L, Yin, H, Nguyen, QVH   +5 more
core   +4 more sources

Disaster Prediction Knowledge Graph Based on Multi-Source Spatio-Temporal Information [PDF]

, 2022
Natural disasters have frequently occurred and caused great harm. Although the remote sensing technology can effectively provide disaster data, it still needs to consider the relevant information from multiple aspects for disaster analysis. It is hard to
Chen, Jiahui, Li, Weichao, Zhang, Wenyue, Ge, Xingtong, Peng, Ling, Wenyue Zhang, Huang, Zhisheng, Weichao Li, Yi Yang, Zhisheng Huang, Xingtong Ge, Jiahui Chen, Ling Peng, Yang, Yi   +13 more
core   +1 more source

PDDL2.1 : An extension of PDDL for expressing temporal planning domains [PDF]

, 2003
In recent years research in the planning community has moved increasingly towards application of planners to realistic problems involving both time and many types of resources.
Maria Fox, Fox, Maria, Long, D., Fox, M., Long, Derek, Derek Long, Long, Derek; id_orcid   +6 more
core   +1 more source

ERGCN: Enhanced Relational Graph Convolution Network, an Optimization for Entity Prediction Tasks on Temporal Knowledge Graphs

Future Internet, 2022
Reasoning on temporal knowledge graphs, which aims to infer new facts from existing knowledge, has attracted extensive attention and in-depth research recently.
Yinglin Wang, Xinyu Xu
doaj   +1 more source