Lmst

Join the conversation on how we can rigorously assess the capabilities of LMs in semantic technologies and structured knowledge generation. 📊🤖

#ELMKE2025 #LanguageModels #KnowledgeEngineering #Evaluation #SemanticWeb #AI #KnowledgeGraphs #LLMs #ESWC2025 #ResponsibleAI #BenchmarkingAI

What is Ontology Engineering?

🧠 Learn how Ontology Engineering structures knowledge for intelligent systems and the Semantic Web.

👉 Click here: https://www.engineersheaven.org/forum/topic/51?title=What-is-Ontology-Engineering?
to visit our website and read the full article.

#OntologyEngineering #SemanticWeb #KnowledgeEngineering #AI #FutureTech #EngineersHeaven

Where content, #knowledgeManagement, and #AI converge, you'll find Michael Iantosca.

As many in the AI world choose probabilistic models like LLMs, Michael takes a deterministic approach to #contentManagement and #knowledgeEngineering, using #ontologies and #knowledgeGraphs to ground content in facts.

This approach embodies his insight that content and the models that describe it are valuable enterprise IP assets.

https://knowledgegraphinsights.com/michael-iantosca/

🥁 Introducing #EKAW24 2nd keynote speaker 🥁
▫️𝐒𝐮𝐳𝐚𝐧 𝐕𝐞𝐫𝐛𝐞𝐫𝐧𝐞▫️

We are looking forward to the keynote
"Is the Search Engine of the Future a Chatbot?" 🔎🤖

Find more information about the keynote talks at https://event.cwi.nl/ekaw2024/keynotes.html

#KnowledgeEngineering #KnowledgeManagement #Keynote

Find more about #EKAW24 𝙏𝙪𝙩𝙤𝙧𝙞𝙖𝙡 on
Semantic Knowledge Modeling -
Ontologies & Vocabularies
at https://metaphacts.com/ekaw24-semantic-modeling-tutorial

#SemanticModeling #Ontologies #Vocabularies #KnowledgeEngineering #Tutorial

A few days left for 𝗣𝗼𝘀𝘁𝗲𝗿𝘀 & 𝗗𝗲𝗺𝗼𝘀!

Submit your

📈 late-breaking results
🔄 on-going projects
🚀 innovative prototypes

P&Ds in #EKAW24 are great opportunity for

💡 invaluable input
✅ effective feedback
🤝 starting collaborations

Check the call at https://event.cwi.nl/ekaw2024/cfpd.html

#Poster #Demo
#KnowledgeEngineering #KnowledgeManagement

𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩 ELMKE
Evaluation of Language Models in
Knowledge Engineering

Submissions:
📰Long 10-15 pages
📄Short 5-9 pages
⏰Deadline September 17

Find more at: https://sites.google.com/view/elmke
#LanguageModels #KnowledgeEngineering #OntologyEngineering #Evaluation #Workshop #EKAW24

One essential conclusion of Giorgia Lodi's keynote at #ISWS2024: #GIGO - the (in)famous Garbage-In-Garbage-Out is a universal computing principle, which also cannot be changed via #AI and #LLMs. Couplig with data, information, and knowledge that is curated by domain experts is essential for constructing dependable (#LLM-based) solutions!
...quoting @kidehen OpenLink Software

#summerschool #dataquality #knowledgegraphs #knowledgeengineering #ai

Conclusions from Giorgia Lodi's keynote at ISWS2024, quoting Kingsley Idehen on the GIGO principle and the importance of curated data, information, and knowledge for dependable LLM solutions.

When using knowledge engineering methodologies,...
- data quality increases
- domain experts start to understand the importance of semantics
- more participation - but understanding is the key challenge
- costs will be rising
- even technicians consider it as too complex for aplications development

Lessons learnt from knowledge engineering presented by Giorgia Lodi in her #ISWS2024 keynote

#knowledgeengineering #knowledgegraphs #ontologies #dataquality #summerschool

When using knowledge engineering methodologies...
data quality increases (also for data not organised in knowledge graphs), Domain experts start to understand the importance of data semantics, More participation of people but a continuous fight on silly details. Finding Agreement is the most challenging task. The sosts are quite high. Years of work for ceeating ontologies and the impression is that the coverage of the current potential knowledge is still not that high. Perceived, also from technicians, too complex for applications development. Full adoption is not as high as we probably expected, with differences from public and private sector.

In the next #ISWS2024 tutorial Aldo Gangemi is addressing the principles of extensional vs. intentional modeling in #knowledgegraphs.

#summerschool #semanticweb #knowledgeengineering

Aldo Gangemi presenting another tutorial on extensional vs intensional modeling of knowledge graphs at ISWS 2024.

Interesting, how knowledge engineering requirements have evolved over time ;-)
from the slides of Paul Groth's tutorial on #knowledgegraph creation at #ISWS2024

referencing Bradley P. Allen, Filip Ilievski, Saurav Joshi, Identifying and Consolidating Knowledge Engineering Requirements, https://arxiv.org/abs/2306.15124

#knowledgegraphs #knowledgeengineering #summerschool

#ESWC2024 closing ceremony led by general chair @albertmeronyo with lots of thanks, acknowledgements, and of course....awards ;-)

#semanticweb #knowledgegraphs #llms #generativeAI #knowledgeengineering #ontologies

Albert Moreño at the ESWC closing ceremony.

Reflections on the Special Track on LLMs for Knowledge Engineering at #ESWC2024.
From my point of view a very valuable contribution to the conference, exchanging our experiences and research efforts as long as there are no established methodologies and evaluations in this field.

#llms #knowledgeengineering #knowledgegraphs #ontologydesign #ontologicalengineering ontologies

Reflections C How do we make a useful benchmark? * ©.g protecting the benchmark * Isthisoutof sample for the LLM? * LWMleaderboard * Useful outside of the community / reproducibility * Whatworks across / independent of LLMs * Where do we get data with some of the tasks? * Availability of data about the process of knowledge engineering * Speedand variability of the LLMs * Move towards rearchitecting KE workflows ; e Need more in-practice human evaluation * Whole workflow evaluation | * Return of methodoloe){ * Small selection of tasks -what are major tasks that are missing? * More outputs when using LLMs meaning more things to evaluate * The Surprising importance of syntax * Where/who are making the mistakes * Environmental impact * The Propogation of Potential bias from LLMs to the knowledge graphs . Documenting the learnings from these studies in astructured way * Studying the changing relationship between knoMedge engineer, LLM, KG . Potentially look at software engineering 2 £ v

Knowledge Engineering is transforming. This is what we're going to need.
...Conclusion of Elena Simperl's keynote at #ESWC2024

#knowledgeengineering #ontologies #knowledgegraphs #semanticweb #llms

Final thoughts * Knowledge engineering is transforming. We need . Mgthodologies w/ stronger focus on hybrid workflows, new roles (prompting), new skills (co-auditing, responsible Al) * Viable Al copilots, multimodal support, scalable to real knowledge graphs * Datasets, benchmarks, and evaluation protocols to improve the technical performance of LLMs in knowledge engineering tasks (e.g. knowledge prompts, multi-turn dialog, safety, user stories, CQs, documentation etc.) * Campaigns to share and reuse data where possible to reduce data-related costs (prompting collectives) » Guidance, best practices to use Al effectively * Mechanisms to demonstrate Al-co-generated knowledge graphs can be trusted ~

FIrst #ESWC2024 Keynote by Elena Simperl on "Knowledge Engineering from people to machines and back" dives into the history of knowledge engineering and reminds us about the many different approaches ranging from people, over more people, gamification, crowdsourcing, automation, etc.

#knowledgeengineering #semanticweb #ontologies #ontologicalengineering #knowledgegraphs

Elena Simperl presenting her keynote at ESWC2024

Tolle Neuigkeiten: Für seine herausragenden Beiträge im Bereich #KnowledgeEngineering wurde #TIB-Direktor und @L3S_Research_Center@wisskomm.social-Mitglied @soeren_auer auf Platz 33 als „#AI 2000 Most Influential Scholar Honorable Mention“ zwischen 2014 und 2023 ausgezeichnet und zählt damit zu den einflussreichsten #KI-Forscher:innen. Herzlichen Glückwunsch! 🎉

Mehr dazu: https://www.tib.eu/de/die-tib/neuigkeiten-und-termine/aktuelles/detail/prof-soeren-auer-zaehlt-zu-den-einflussreichsten-ki-forschern

Information Service Engineering is the denomination of our research group at @fiz_karlsruhe as well as of my chair at @KIT_Karlsruhe
...and this is how #Midjourney imagines how "Information Service Engineering" might look like ;-)

Our research focus lies on on #knowledgegraphs
#informationextraction
#knowledgeengineering
#ontologies #researchdatamanagement
#exploratorysearch #semanticsearch
#nlp #aiart #generativeai @sourisnumerique @tabea @sashabruns @MahsaVafaie @enorouzi

Information service engineering as imagined by midjourney

📢 Check out the call for papers for the special issue of the new Neurosymbolic AI Journal on "Knowledge Graphs and Neurosymbolic AI".
📌 Deadline May 31, 2024.
📗Contributions may include full papers, dataset descriptions, survey papers, application reports and reports on tools and systems.
Editors: Marta Sabou, Raghava Mutharaju, Frank van Harmelen

https://neurosymbolic-ai-journal.com/content/call-papers-special-issue-knowledge-graphs-and-neurosymbolic-ai

#neurosymbolicAI #AI #knowledgeengineering #knowledgegraphs #semanticweb #machinelearning #humancentric
via #linkedIn

Cover of the Neurosymbiólic Artificial Intelligence Journal, IOS Press.

#ExplainableAI for #LLM systems whether chatbots or backend components is very important for trustworthiness and debugging.

One of the most effective ways to do it is to make the chatbot refer to sources of facts. Tag every RAG document partial with an anchor, and tell the chatbot refer to them. Then you can show in a final presentation a link to the document part used.

In a document index you similarly want to include metadata for partials, so that a user can click "show the whole document" and navigate the information if they want to see where the content came from.

It's all very well explainable but requires a bit of work in #KnowledgeEngineering and #LinkedData.

#KnowledgeEngineering

Client Info