New Tech Briefs Released: AI & Knowledge Graph Advances
The STELAR project continues its exploration of AI and data innovations with the release of two new tech briefs. These latest insights focus on advancing schema and entity matching, as well as improving accessibility to knowledge graphs. The work is driven by leading researchers contributing to AI, knowledge graphs, and data interoperability.
Read on for details about the University of Athens’ work on schema matching with pyJedAI and natural-language querying with STELAR-QA.
University of Athens: Expertise in Semantic Data Tools
The two tech briefs in this series are written by the National and Kapodistrian University of Athens (UoA). Their Artificial Intelligence team at the Department of Informatics and Telecommunications contributes to STELAR by providing tools for schema mapping, ontology alignment, and entity matching. These tools tackle semantic interoperability and data linking challenges, drawing on the team’s expertise in geospatial and spatio-temporal linked data.
In these tech briefs, they explore topics such as schema and entity matching, along with advancements in the STELAR Knowledge Graph.
Tech Brief #5: Schema and Entity Matching with pyJedAI
In this tech brief, George Papadakis, an advanced Python framework that makes schema and entity matching easier and more efficient. Whether integrating data from diverse sources or linking different descriptions of the same entity, pyJedAI leverages deep learning and natural language processing techniques to streamline the process. With its powerful Filtering-Verification framework, pyJedAI ensures scalability and speed, even when handling large datasets.
The brief covers key features, installation options, and highlights how pyJedAI can address complex data integration tasks efficiently.
Tech Brief #6: STELAR-QA: A Natural Language Interface for the STELAR Knowledge Graph
Sergios-Anestis Kefalids, a PhD candidate and Research Assistant at UoA, presents STELAR-QA, a question-answering engine for the STELAR Knowledge Graph. By combining advanced language models and natural language processing techniques, it improves accessibility for novice users and boosts expert productivity. The brief details how the system streamlines data retrieval to extract insights.
Conclusion
These tech briefs reflect STELAR’s commitment to addressing key challenges in AI, data interoperability, and knowledge accessibility. By sharing these insights, the project fosters collaboration and knowledge exchange across research and industry communities.
Stay tuned for more tech briefs – in the meantime, you can read more about our previous ones here:
Follow us on LinkedIn, Instagram, Facebook, and X to stay updated!
