Recent advancements in knowledge graph research are focusing on enhancing the capabilities of these structures for a range of applications, particularly in link prediction and information retrieval. Techniques such as THOR are pushing the boundaries of hyper-relational knowledge graphs by enabling inductive link prediction, which allows for generalization beyond specific vocabularies. Meanwhile, approaches like TIER are integrating hierarchical knowledge into text-rich networks, improving semantic coherence and interpretability. The introduction of frameworks like SynergyKGC addresses the challenges of topological heterogeneity in knowledge graph completion, enhancing relational reasoning across diverse graph structures. Additionally, innovations such as TKG-Thinker are leveraging reinforcement learning for dynamic reasoning over temporal knowledge graphs, improving the accuracy of time-sensitive question answering. Collectively, these efforts are not only refining the theoretical underpinnings of knowledge graphs but also addressing practical challenges in data integration and machine learning, paving the way for more robust and versatile applications in various domains.
Knowledge graphs (KGs) have become a key ingredient supporting a variety of applications. Beyond the traditional triplet representation of facts where a relation connects two entities, modern KGs obse...
Hierarchical knowledge structures are ubiquitous across real-world domains and play a vital role in organizing information from coarse to fine semantic levels. While such structures have been widely u...
Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models (LLMs) demonstrate significant potential...
Knowledge Graph Completion (KGC) fundamentally hinges on the coherent fusion of pre-trained entity semantics with heterogeneous topological structures to facilitate robust relational reasoning. Howeve...
Domain-specific knowledge graphs (DKGs) often lack coverage compared to general knowledge graphs (GKGs). To address this, we introduce Domain-specific Knowledge Graph Fusion (DKGF), a novel task that ...
Leveraging Large Language Models (LLMs) for Knowledge Graph Completion (KGC) is promising but hindered by a fundamental granularity mismatch. LLMs operate on fragmented token sequences, whereas entiti...
Datasets for the experimental evaluation of knowledge graph refinement algorithms typically contain only ground facts, retaining very limited schema level knowledge even when such information is avail...
Documentation of airport operations is inherently complex due to extensive technical terminology, rigorous regulations, proprietary regional information, and fragmented communication across multiple s...
Semantic data and knowledge infrastructures must reconcile two fundamentally different forms of representation: natural language, in which most knowledge is created and communicated, and formal semant...
Scientific reviews are central to knowledge integration in materials science, yet their key insights remain locked in narrative text and static PDF tables, limiting reuse by humans and machines alike....