Jiaoyan Chen

The University of Manchester, UK

Title: Embedding Complex Knowledge: From Geometric to Language Models

Abstract: Semantic embedding is to represent symbolic knowledge as vectors, which can dramatically extend the tools and algorithms for processing and utilising symbolic knowledge. In the report, I will focus on some recent embedding methods for ontologies of Web Ontology Language, which are equipped with different kinds of semantics including Description Logic, hierarchical graph structure and literals. The contents vary from geometric embeddings for logical and hierarchical relationships, to language model-based embeddings for text-equipped ontologies.

Short Bio: Dr. Jiaoyan Chen is Senior Lecturer (Associate Professor) in Department of Computer Science, The University of Manchester. Before joining The University of Manchester in 2022, he worked as a Senior Researcher in University of Oxford since 2017 and got his PhD in Computer Science and Technology in Zhejiang University. Jiaoyan’s research focuses on Knowledge Graph, Ontology, Semantic Web and AI. His publications have attracted over 5000 citations with an H-Index of 41 by Google Scholar, and his work has been funded by an EPSRC New Investigator Award and an EPSRC normal grant.

Vasilis Efthymiou

Harokopio University of Athens & FORTH-ICS, Greece

Title: Semantic Enrichment of Data Using Knowledge Graphs

Abstract: Knowledge graphs have become essential for moving beyond raw data to contextualized, machine-understandable knowledge. This talk explores how semantic enrichment - linking structured and unstructured data to external knowledge graphs - enables richer interpretation, reasoning, and discovery. By infusing data with semantics, we can unlock more expressive query answering, natural language interaction, and robust AI applications. Recent advances will be outlined to show how semantic enrichment turns isolated datasets into powerful knowledge-driven systems.

Short Bio: Vasilis Efthymiou is an Assistant Professor at Harokopio University of Athens and an Affiliated Researcher at FORTH-ICS. He received his PhD from the Computer Science Department of University of Crete for research on entity resolution in the Web of Data. Before joining HUA, he was a postdoctoral researcher at IBM Research Almaden, working on data management and AI, for providing natural language interfaces to data. After his research internship at IBM T.J. Watson Research Center, NY, USA, on matching Web tables to Knowledge Graphs, he has been co-organizing the SemTab challenge at ISWC and the TaDA workshop at VLDB. He has recently been appointed as the Coordinator of W3C Greek Office.

Ningyu Zhang

Zhejiang University, China

Title: Knowledgeable Agents

Abstract: At present, research on language model agents is entering a golden period for the practical implementation of reasoning and planning technologies. However, in most real-world applications, reasoning and planning often suffer from instability and unreliability due to the lack of domain knowledge, leading to blind trial-and-error, planning hallucinations, and other errors that severely impact user experience. This talk will focus on knowledge-augmented language model agent technologies, introducing methods for trajectory synthesis, reliable planning, and memory updating based on knowledge augmentation.

Short Bio: Ningyu Zhang is an associate professor at Zhejiang University, leading the group about KG and NLP technologies. He has supervised to construct an information extraction toolkit named DeepKE (4.1K+ stars on Github). His research interest include knowledge graph and natural language processing. He has published many papers in top international academic conferences such as Natural Machine Intelligence, Nature Communications, theWebConf, ISWC, NeurIPS, ICLR, AAAI, IJCAI, ACL, ENNLP. He has served as Area Chair for ACL/EMNLP/ICLR/NeurIPS/KDD, ARR Action Editor, Senior Program Committee member for IJCAI 2023, Program Committee member for theWebConf, ISWC.