Thrilled to announce that our team has had 3 papers accepted at #KCAP2025 (www.k-cap.org/2025/) incl. an approach for knowledge extraction from text + test bed for uncertain knowledge reconciliation
@orange.com #OrangeResearch

'Uncertainty Management in the Construction of Knowledge Graphs: A Survey' now available in TGDK!
doi.org/10.4230/TGDK...
This paper explores how to handle uncertainty/knowledge deltas and carry out the crucial task of knowledge fusion
#OrangeResearch
Work done with Lucas Jarnac and Miguel Couceiro

Our latest research paper, "Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends" is now available on Arxiv
arxiv.org/abs/2501.02235
Collaboration between @orange.com and @mlia-isir.bsky.social

You will be integrated into a research team focusing on structuring knowledge in enterprise knowledge graphs and enhancing their value using large language models.
#PhDLife #ResearchOpportunities #AI #KnowledgeGraphs #LLM #GenerativeAI #LifeAtOrange #Belfort

2️⃣ Design of an Ontological Framework for Capturing Knowledge Related to Business Models. Use knowledge graphs and LLMs to model business concepts and improve information retrieval and analysis. Learn more: orange.jobs/jobs/v3/offe...

1️⃣ Knowledge Integration and Traceability in a GraphRAG-Based Question-Answering System. Improve robustness, precision, and traceability of Q/A systems by combining LLMs and enterprise knowledge graphs. Learn more: orange.jobs/jobs/v3/offe...

Join our research team at Orange: two PhD positions available this year on enhancing enterprise knowledge graphs with large language models! 📚 -->

📡 At Orange, we're pushing the boundaries of connectivity!
Thanks to our partnership with Telesat, we'll be leveraging the LEO Lightspeed satellite constellation to offer ever more powerful connectivity to businesses and telecom operators.
👉 newsroom.orange.com/orange-and-t...

Documents often blend text and tables, offering complementary insights. Our challenge aims to harness this synergy for joint knowledge extraction and knowledge graph enrichment.
Stay tuned for more details! We can't wait to see your amazing contributions!

Thrilled to announce that our research group will be running the TRIPLET challenge at #ISWC2025! 🗾
@rtroncy.bsky.social EURECOM @orange.com @iritoulouse.bsky.social IBM
#SemanticWeb #KnowledgeGraphs #InformationExtraction #AIChallenge

The Holonet Galactic Encyclopedia has been named "Tool of the Week" by #Wikidata! 🎉
m.wikidata.org/wiki/Wikidat...
Huge thanks for the spotlight! 🙌 Stay tuned, fellow #StarWars fans and #KnowledgeGraph enthusiasts, more features are coming soon! 🌌
Try it: holonetgalacticmap-frontend.vercel.app

Join the journey!
This project is a labor of love and learning. Explore the galaxy, use the data, and share your thoughts!
holonetgalacticmap-frontend.vercel.app #wikidata @wookofficial.bsky.social

What’s next?
I’m just getting started! Coming soon:
-More data about planets and their connections to Star Wars media
-More links with characters, ships, and events
-An intuitive graphical atlas to visually navigate regions, systems, and planets

From 45 planets to over 700 in Wikidata! When I started more than a year ago, Wikidata had ~45 SW planets. Today, over 700 planets are listed, complete with key data like coordinates, appearances in media, and links to Wookieepedia. Check it out: holonetgalacticmap-frontend.vercel.app/planets/table

Why focus on Star Wars planets?
Planets are the foundation of galactic lore, each with its own story, features and connections to iconic characters and events. It’s also a fun dataset to use for educational purposes like teaching SPARQL! (examples here holonetgalacticmap-frontend.vercel.app/sparql)

I've been working on an initiative to feed Wikidata with knowledge about the Star Wars universe, starting with planets. Let me share the story, the progress, and the vision. 🧵