Workshops
The following is a list of accepted Workshops. Please visit the relative web pages to have a look at the Workshop calls.
KNUMS
First Workshop on Knowledge Management for Numerical Modeling, Measurement & Simulation
k-nums.github.io
Organizers: Benno Kruit (VU Amsterdam), Victoria Deleger (University of Amsterdam), João Moreira (University of Twente)
Keywords / Topics of interest: Knowledge Management for Numerical Data, Measurement Knowledge, Numerical Modeling, Digital Twins, IoT, Timeseries, Model Metadata Management, Applications
Types of submission: Long (15 page) and short/vision (7 page) papers
Deadlines: September 17, 2024 (Paper submission)
Website URL: https://k-nums.github.io/ekaw/2024/
X-TAIL
eXtraction and eXploitation of long-TAIL Knowledge with LLMs and KGs
xtail-workshop.org/
Organizers and affiliations: Arianna Graciotti (University of Bologna), Alba Morales Tirado (The Open University), Valentina Presutti (University of Bologna), Enrico Motta (The Open University)
Keywords: long-tail knowledge, RAG, knowledge probing, LLM, knowledge graphs
Types of submission: Long papers (10-15 pages), Short papers (5-9 pages)
Deadlines: Abstract Registration Deadline: September 8th, 2024; Workshop Papers Submission Deadline: September 17th, 2024; Workshop Papers Notification: October 15th, 2024; Early Bird Registration: October 17th, 2024; Workshop Papers Camera Ready: November 20th, 2024; Conference Days: November 26-28th, 2024
Topics of interest: Knowledge Extraction from non-standard unstructured sources; Knowledge Probing; Multi-modal Retrieval-augmented Generation (RAG) techniques
Website URL: https://www.xtail-workshop.org/
ELMKE
Workshop on Evaluation of Language Models in Knowledge Engineering
elmke
Organizers and affiliations: Bohui Zhang (King’s College London), Yuan He (University of Oxford), Reham Alharbi (University of Liverpool)
Keywords: Language Models, Knowledge Engineering, Ontology Engineering, Evaluation, Benchmarks, Dataset
Types of submission: long papers (10-15 pages), short papers (5-9 pages)
Deadlines: Papers Submission Deadline: September 17, 2024; Papers Notification: October 15, 2024; Camera Ready: November 20, 2024
Topics of interest: Novel evaluation approaches for Language Models (LMs) in Knowledge Engineering (KE) tasks; Challenges and limitations of existing evaluation methods for LMs in KE; Examination of human factors in the evaluation of LMs in KE tasks; Datasets and benchmarks for LMs evaluation in KE tasks; Exploration of hybrid evaluation methods; Methods and metrics for evaluating the trustworthiness, interpretability, and explainability of LM-generated results
Website URL: https://sites.google.com/view/elmke
K-MiN
First Workshop on Structured Knowledge in Newsrooms
k-min.info/
Organizers and affiliations: Dr Reshmi G Pillai (Vrije University Amsterdam), Dr. Laurence Dierickx (University of Bergen / Université Libre de Bruxelles)
Keywords: Journalistic Knowledge Platforms, Knowledge graphs, Large Language Models, Journalistic AI, Ethics
Types of submission: Long (10-15 pages) and Short (5-9 pages) papers describing novel ideas or applications demonstrating the adoption of knowledge management tools and techniques in newsroom tasks; description of application of such existing tools in the context of newsroom knowledge with real-world data and real users; ethical considerations related to developing and adopting these technologies in newsrooms
Deadlines: Submission link open: July 19th 2024; Paper Submission deadline: September 17th 2024; Acceptance notification: October 20th 2024; Camera-ready deadline: November 20th, 2024; Conference dates: November 26-28, 2024
Website URL: k-min.info/
Tutorials
Conversational Knowledge Capture Using the KNOW Ontology
ekaw2024.asimov.so
Organizers and affiliations:
Dr. Tolga Çöplü, Haltia.AI (tolga@haltia.ai)
Dr. Tolga Çöplü is an expert in integrating communication technologies with machine learning, boasting over two decades of research and development experience. His focus is on the practical application of neurosymbolic AI to enhance the personalization and efficiency of AI systems. Dr. Çöplü has authored numerous academic papers and is pivotal in applying symbolic AI with large language models.
Arto Bendiken, Haltia.AI (arto@haltia.ai, https://ar.to)
Arto Bendiken brings over 25 years of experience in software engineering and artificial intelligence, with a specialization in Semantic Web technology and knowledge graphs. His pioneering work has significantly influenced the development of decentralized graph database technologies. As co-founder and CTO of Dydra, he developed solutions that now support Haltia.AI’s AI systems, and he leads the design of the KNOW ontology.
Andrii Skomorokhov, Haltia.AI (andrii.skomorokhov@haltia.ai)
Andrii Skomorokhov has over 15 years of experience developing complex data management systems and AI applications. At Haltia.AI, he focuses on applying Large Language Model (LLM) adapters to construct comprehensive knowledge graphs from extensive datasets, enhancing AI personalization and mobile assistant technologies. His research contributes to the development of privacy-centric, on-device AI solutions.
Keywords: Conversational knowledge capture, ontology-guided knowledge capture, KNOW ontology, symbolic representation, knowledge graphs, large language models.
Target audience:
- Early-stage researchers in neurosymbolic AI
- Experienced Semantic Web/Knowledge Graph researchers
- AI practitioners in real-world applications
- Researchers interested in personal data extraction from LLM conversations
- Professionals seeking ontological knowledge capture techniques
Why participate?
- Understand the fundamentals of neurosymbolic AI.
- Gain skills in generative AI and its applications.
- Learn to apply advanced knowledge capture in real-world scenarios.
- Master different approaches to the generation of personal information in the era of generative AI
- Explore integration with the KNOW ecosystem for enhanced AI personalization
Requirements to participate:
Participants should bring laptops or tablets to engage with provided digital materials:
- Handouts and printed materials will be provided
- Code and notebooks accessible on GitHub
Participants are encouraged to review the KNOW ontology webpage and the GitHub repository prior to attending the tutorial:
Contents of the Tutorial:
- Overview and Introduction: Framing the neurosymbolic challenge and its relevance.
- Neurosymbolic Synthesis
- The KNOW Ontology in Action
- Hands-on Ontology-Guided Knowledge Capture
- Discussion on the future of AI research and applications
Tutorial webpage URL: https://ekaw2024.asimov.so
MUHAI Tutorial
Enabling Meaning and Understanding in Human-centric AI
kmitd.github.io/muhai-tutorial
Organizers and affiliations:
Ilaria Tiddi - Vrije Universiteit Amsterdam
Rachel Ringe - University of Bremen
Carlo Santagiustina - SciencesPo Medialab Paris
Remi van Trijp - Sony CSL Paris
Keywords: Human-centric AI, Natural Language Processing, Virtual Reality, Knowledge Graphs, Language Models.
Target audience: The tutorial aims for a broad audience in terms of topics. We are looking for participants that are interested in neuro-symbolic integration, speech and natural language processing, knowledge modelling and construction, narratives and event-centric knowledge graphs, but also VR, robotics, social scientists and cooking enthusiasts are welcome. We do not expect more than 30 participants.
Why participate? It’s a demo-showcase where one can see several AI technologies for human-centric AI in action. Also, we have "toetjes" for the participants!
Requirements to participate: N/A
Contents of the tutorial: See content & tentative program on the website.
Tutorial webpage URL: https://kmitd.github.io/muhai-tutorial/
Tutorial on Creating and Accessing Knowledge Graphs for Action Parameterisation
https://kr3-workshop.net/ekaw-tutorial/
Organizers and affiliations:
Michaela Kümpel (University of Bremen)
Jan-Philipp Töberg (Bielefeld University)
Ilaria Tiddi (Vrije Universiteit Amsterdam)
Philipp Cimiano (Bielefeld University)
Enrico Motta (Open University)
Michael Beetz (University of Bremen)
Keywords: Actionable Knowledge Graphs, Robot Action Execution, Task Parametrisation, Knowledge Acquisition
Target audience: Everyone who is working on the intersection of knowledge engineering and agent applications.
Why participate? We present an approach to make knowledge graph content actionable in agent applications with lots of practical examples, and encourage you to bring in your own struggles and solutions for discussion.
Requirements to participate: A Laptop or Smartphone with administrative rights is needed to execute the practical examples.
Contents of the tutorial: We present the problem of making knowledge actionable in agent applications in a very challenging example and guide the participants in how to use our 5 step methodology in an example use case. We will include active participation sessions to adapt the approach to other problems and also make room to discuss possible collaborations.
Semantic Knowledge Modeling - Ontologies & Vocabularies
https://metaphacts.com/ekaw24-semantic-modeling-tutorial
Organizers and affiliations:
Dr. Peter Haase, Irina Schmidt (metaphacts GmbH)
Keywords: semantic modeling, ontologies, vocabularies, knowledge engineering
Target audience:
- Practitioners and interested novices in semantic modeling / knowledge engineering
- Academics and industry professionals
- Subject matter experts (SMEs)
Why participate?
- Learn how to build and manage semantic models and ontologies to drive explainable and trustworthy business decisions.
- Explore a new approach to semantic knowledge modeling with metaphactory's user-friendly interface.
- Engage with practical examples and hands-on exercises to enhance your skills in creating, exploring, and managing knowledge graph assets.
- Understand the integration of data catalog and ontology publishing for better discovery and compliance.
Requirements to participate:
Participants should bring their own laptops. Web-based access to the required software will be provided.
Contents of the tutorial:
- Visual creation and management of OWL/SHACL ontologies for domain experts and business users.
- Creation and management of SKOS vocabularies to capture business-relevant terms.
- Data catalog integration: managing and importing existing dataset metadata.
- Publishing ontologies and vocabularies for discovery, including class and term template pages.
- Governance, versioning, and compliance workflows.
- Instance data management using semantic forms and visual authoring.
- Model-driven app building with a low-code approach.