10 papers
Ontology Refinement with Embeddings and LLMs: A Case Study on CASTON
Hui Yang, Ziyu Li, Xuan Liu +3
Ontologies are widely used to represent and organize complex knowledge in domains such as biomedicine and healthcare. However, constructing reliable ontologies remains challenging,…
NeurOWL: An LLM-Based Neural-symbolic Framework for Incomplete OWL Ontology Reasoning
Hui Yang, Jiaoyan Chen, Yiping Song +2
OWL ontologies provide a formal knowledge representation framework that enables semantic reasoning, and have been widely adopted across domains such as healthcare and bioinformatic…
AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching
Yiping Song, Jiaoyan Chen, Renate Schmidt +2
Ontology matching (OM) has traditionally been formulated as either equivalence discovery or subsumption matching. The existing OM systems identify only one type of semantic corresp…
Large Language Model for OWL Proofs
Hui Yang, Jiaoyan Chen, Uli Sattler
The ability of Large Language Models (LLMs) to perform reasoning tasks such as deduction has been widely investigated in recent years. Yet, their capacity to generate proofs-faithf…
Unbiased Platform-Level Causal Estimation for Search Systems: A Competitive Isolation PSM-DID Framework
Ying Song, Yijing Wang, Hui Yang +12
Evaluating platform-level interventions in search-based two-sided marketplaces is fundamentally challenged by systemic effects such as spillovers and network interference. While wi…
Hierarchical Retrieval with Out-Of-Vocabulary Queries: A Case Study on SNOMED CT
Jonathon Dilworth, Hui Yang, Jiaoyan Chen +2
SNOMED CT is a biomedical ontology with a hierarchical representation, modelling terminological concepts at a large scale. Knowledge retrieval in SNOMED CT is critical for its appl…
Language Models as Ontology Encoders
Hui Yang, Jiaoyan Chen, Yuan He +2
OWL (Web Ontology Language) ontologies which are able to formally represent complex knowledge and support semantic reasoning have been widely adopted across various domains such as…
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora
Jiaxin Bai, Wei Fan, Qi Hu +17
We present AutoSchemaKG, a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas. Our system leverages large language models t…
RegD: Hierarchical Embeddings via Dissimilarity between Arbitrary Euclidean Regions
Hui Yang, Jiaoyan Chen
Hierarchical data is common in many domains like life sciences and e-commerce, and its embeddings often play a critical role. While hyperbolic embeddings offer a theoretically grou…
TransBox: EL++-closed Ontology Embedding
Hui Yang, Jiaoyan Chen, Uli Sattler
OWL (Web Ontology Language) ontologies, which are able to represent both relational and type facts as standard knowledge graphs and complex domain knowledge in Description Logic (D…