Program
Day 1 – May 26th 2024
Day 2 – May 27th 2024
Workshops
Workshop on metadata and research management for linked open science – DaMaLOS 2024
Organizers: Leyla Jael Castro – ZB MED Information Centre for Life Sciences (Germany), Sonja Schimmler – Fraunhofer FOKUS & TU Berlin (Germany), Danilo Dessì – GESIS (Germany) and Dietrich Rebholz-Schuhmann – ZB MED Information Centre for Life Sciences (Germany)
Website: https://zbmed.github.io/damalos/
Scientific research involves various digital objects including publications, software, data, workflows and tutorials (i.e., research artifacts), all key to FAIRness, reproducibility and transparency. The research lifecycle, from questions and hypotheses to results and conclusions, requires data production, collection, and transformation, a process commonly supported by software, workflows and tutorials. For this cycle to prosper, we require Research Management Plans (RMPs) including data, software, machine learning (DMPs, SMPs, MLMPs) and metadata supporting the FAIR (data) principles and its extensions (e.g., software, workflows) as well as additional coverage for reproducibility, transparency, trustability, explainability, i.e., *ilities. All sorts of research artifacts are needed to fully realize Linked Open Science, i.e., Open Science plus Linked Open Data (LOD) principles –data here understood in a very broad sense covering any research outcome. LOD principles, aka LOD 5 stars, follow objectives overlapping with FAIR and Open Science (e.g., LOD includes “openness” and usage of “non-proprietary open formats”). In DaMaLOS we will explore requirements for research artifacts and their corresponding management plans to effectively instantiate an integrated layer supporting Linked Open Science. DaMaLOS welcomes contributions aligned to the following topics: machine-actionable research plans; machine/deep learning approaches around rich metadata; FAIRification; FAIR by design (e.g., Research Objects, SignPosting, FDOF); FAIR tooling; recognition, publication and citation for all research artifacts, and scientometrics beyond the scholarly publication (i.e., combining the different research artifacts for research assessment and impact).
Fifth International Workshop on Knowledge Graph Construction (KGCW2024)
Organizers: David Chaves-Fraga – University of Santiago de Compostela (Spain), Anastasia Dimou – KU Leuven (Belgium), Ana Iglesias-Molina – Universidad Politécnica de Madrid (Spain), Dylan Van Assche – Ghent University (Belgium) and Umutcan Serles – University of Innsbruck (Austria)
Website: https://w3id.org/kg-construct/workshop/2024
More and more knowledge graphs (KGs) are constructed for private use, e.g., Google, or public use, e.g., DBpedia, Wikidata. While many solutions were proposed to construct KGs from existing data on the Web, there is still no mature systems to automate the rules definition nor systematic evaluations to compare the performance and resource usage of the different systems independently of the mapping language they use or the way they construct the knowledge graph (materialization or virtualization). Addressing the challenges related to KG construction requires both the investigation of theoretical concepts and the development of systems and methods for their evaluation. The Knowledge Graph Construction Workshop (KGCW) has a special focus this time on novel techniques, frameworks, architectures, and tools for the new extensions of RML such as RDF Collections and Containers, and RDF-Star support and the newest version of the RDF Mapping Language (RML) in general. The workshop includes a keynote, as well as (research, in-use, experience, position, system) paper presentations, demo jam, and break-out discussions. This year, we will celebrate the 2nd edition of the KG Construction Challenge, where an evaluation setup will be provided to the participants to compare the different systems for KG construction. Our goal is to provide a venue for scientific discourse, systematic analysis, and rigorous evaluation of languages, techniques, and systems, as well as practical and applied experiences and lessons learned for constructing knowledge graphs from academia and industry. The workshop complements and aligns with the activities of the W3C Community Group on KG construction.
SemDH2024: First International Workshop of Semantic Digital Humanities
Organizers: Oleksandra Bruns – FIZ Karlsruhe & KIT (Germany), Andrea Poltonieri – University of Bologna (Italy), Lise Stork – Vrije University Amsterdam (Netherlands) and Tabea Tietz – FIZ Karlsruhe & KIT (Germany)
Website: https://semdh.github.io/
Exploration, analysis, and preservation of the rich cultural and historical tapestry of the world are essential for our understanding of humanity’s past and shaping our future. In recent years, there has been increased interest in the creation and application of Ontologies, Knowledge Graphs, and other Semantic Web Technologies within Cultural Heritage (CH) and Digital Humanities (DH). However, to date, the distinct areas of expertise, methodologies and traditions across the fields have led to a noticeable gap between tech solutions and humanities’ needs. The aim of the International Workshop of Semantic Digital Humanities (SemDH) is to bridge this division and encourage closer collaboration and networking across diverse fields. To accomplish this goal, we invite all members of Semantic Web, CH and DH communities actively involved in the development of systematic approaches and advanced technologies for handling heterogeneous, diverse and challenging humanities data. This includes, but is not limited to, constructing and utilizing of knowledge graphs for the humanities, extracting and representing knowledge from historical texts, data linking across disciplines, enriching semantics of historical records and biographies, analyzing social networks, ontology adoption, extension and evaluation for specific domains. In addition, it includes the exploitation of recent technologies, e.g. LLM(s), in the context of semantic technologies, to tackle the diverse challenges associated with working with historical data. We welcome presentations that not only focus on technological endeavours but also explore the analysis of CH and DH data landscape through the perspective of philosophical, historical, social, and other research questions. Apart from research, resource and work-in-progress papers, we encourage the audience to submit panel proposals. By this, authors will be provided with a platform to share and discuss their challenges and/or showcase research findings by gaining immediate feedback from diverse perspectives encompassing computer science, humanities, and cultural heritage. This interactive environment will foster a dynamic and interactive space for knowledge exchange and collaboration.
WISDOMS: Workshop on Integrating the Semantics of Data, Ontologies, Moral and cultural values and their Societal impact
Organizers: Stefano De Giorgis – University of Bologna & ISTC-CNR (Italy), Luana Bulla – University of Catania & ISTC-CNR (Italy), Maria Hedblom – University of Jönköping (Sweden) and Luc Steels – Institute for Evolutionary Biology (CSIC,UPF) (Spain)
Website: https://wisdoms-workshop.github.io/
The growing influence of AI in our daily lives has transformed both the digital landscape and the way we extract, represent, and generate information. As a consequence, it highlighted the demand for ethical and reliable AI, supported by ethical guidelines and requirements recognized by governments, industry, the public, and academia. The surge in LLM usage, in particular, has made it increasingly crucial to address the alignment of AI tools to moral and cultural human values, especially when hybridizing knowledge structures and semantic data with generative AI, following EU’s objective of realizing AI applications that are dependable, robust, explicable, ethically guided, and therefore trustworthy. The first edition of WISDOMS, the Workshop on Integrating the Semantics of Data, Ontologies, theories of Moral values and their Societal impact, aims to provide an interdisciplinary crossroad for researchers, practitioners, and experts to explore the convergence of ethics, moral and cultural values, and socio-behavioral norms with hybrid knowledge structures and generative AI. WISDOMS offers an opportunity to engage in interdisciplinary discussions at the intersection of ethics, morality, knowledge graphs, semantic technologies, linked open data, and generative AI. This workshop accepts contributions on several topics, such as (but not limited to): Knowledge Representation and Extraction of moral, cultural and social values; Grounded World Models, with a particular focus on Ethics and Morality; Morally Informed Decision Making; Generative models of moral behavior; Formal Representation of Socio-behavioral theories for Social and Legal Norms, etc.
The Second International Workshop Semantics in Dataspaces (SDS 2024)
Organizers: Johannes Theissen-Lipp – RWTH Aachen University & Fraunhofer FIT (Germany), Edward Curry – NUI Galway (Ireland), Pieter Colpaert – Ghent University (Belgium) , Sulayman K. Sowe – RWTH Aachen (Germany) and Stefan Decker – Fraunhofer FIT (Germany)
Website: https://dbis.rwth-aachen.de/SDS24/
Dataspaces have emerged as frameworks that facilitate seamless and trusted data sharing and have recently received attention from politicians, researchers, and practitioners. Efficient data sharing within dataspaces requires semantic interoperability, for which the Semantic Web community has a long history of developing RDF-based solutions. The Semantic Web Dataspaces (SDS) 2024 workshop aims to foster collaborative efforts to develop semantic methods and solutions tailored for dataspaces. The workshop will improve the expressiveness and standardization of semantic methods and solutions for dataspaces, facilitate the development of shared semantic resources for dataspaces, explore the integration of semantic technologies into dataspace architectures, and promote the adoption of semantic approaches in dataspace implementations. The SDS 2024 workshop will serve as a platform to bring together a diverse community of researchers and practitioners in this area. Through engaging discussions and collaborative efforts, the workshop aims to advance the state of the art in semantics for dataspaces.
2nd International Workshop on Data Management for Knowledge Graphs (DMKG 2024) – canceled
Organizers: Christian Aebeloe – Aalborg University (Denmark), Amr Azzam – WU Vienna (Austria), Olaf Hartig – Linköping University (Sweden) and Katja Hose – TU Wien (Austria)
Website: https://dmkg-workshop.github.io/
The rapid adoption of knowledge graphs over the past years, both in the open data domain as well as the industry, calls for novel data management solutions to accommodate the ever increasing amounts of data. The growing interest in knowledge graphs, driven by popularity of semantic technologies, further highlights the need for scalable and efficient solutions for management of knowledge graphs in distributed, federated, and centralized environments. After a successful first edition of the workshop in 2023, the DMKG 2024 workshop once again invites novel research and advances in scalable data management solutions for large-scale knowledge graphs. Such data management solutions include techniques for storage and indexing, partitioning for decentralized/centralized systems, archiving and versioning, validation with SHACL/ShEx, or federated data management. We welcome a broad range of papers including full research papers, vision papers, negative results, and system demonstrations. The main goal of the workshop is to bring together both early-stage and established researchers as well as industrial partners in order to facilitate communication and collaboration between partners in different domains on the issues relating to scalable data management techniques for large-scale knowledge graphs.
3rd International Workshop on Knowledge Graph Generation from Text
Organizers: Sanju Tiwari – BVICAM (India) & UAT (Mexico) and Nandana Mihindukulasooriya – IBM Research (USA)
Website: https://aiisc.ai/text2kg2024/
Knowledge Graphs are getting traction in both academia and in the industry as one of the key elements of AI applications. They are being recognized as an important and essential resource in many downstream tasks such as question answering, recommendation, personal assistants, business analytics, business automation, etc. Even though there are large knowledge graphs built with crowdsourcing such as Wikidata or using semi-structured data such as DBpedia or Yago or from structured data such as relational databases, building knowledge graphs from text corpora still remains an open challenge. The recent advancements in large language models opens up new opportunities to generate knowledge graphs but also introduces new challenges such as hallucinations. The workshop welcomes a broad range of papers including full research papers, negative results, position papers, dataset, and system demos examining the wide range of issues and processes related to knowledge graphs generation from text corpora including, but not limited to entity linking, relation extraction, knowledge representation, and Semantic Web. Papers on resources (methods, tools, benchmarks, libraries, datasets) are also welcomed.
The 2nd Knowledge Graphs for Sustainability Workshop – KG4S
Organizers: Eva Blomqvist – Linköping University (Sweden), Pascal Hitzler – Kansas State University (USA), Raúl García-Castro – Universidad Politécnica de Madrid (Spain), María Poveda-Villalón – Universidad Politécnica de Madrid (Spain) and Daniel Hernandez – University of Stuttgart (Germany)
Website: https://2024.kg4s.org/
This workshop intends to gather researchers and industry stakeholders to create a meeting point between Web of Data technologies and sustainability research, to boost the potential contribution of Web technologies, such as Knowledge Graphs (KGs), towards sustainability. The first edition of the workshop was held at The Web Conference 2023, in Austin (TX). In this second edition, the workshop will continue to focus on the identification of challenges and opportunities in combination with, but not limited to, the presentation of preliminary research results from both academia and industry. The workshop will take a broad perspective on sustainability, including ecological, economical and social sustainability, as also specified by the UN sustainability goals. We aim for a full-day workshop, with both an invited keynote presentation and paper presentations, as well as more interactive sessions, such as posters and demos, and discussions in the form of breakout groups in order to obtain as one of the workshop outcomes a research roadmap in the area of knowledge graphs for sustainability.
Workshop on Natural Scientific Language Processing and Research Knowledge Graphs
Organizers: Georg Rehm – DFKI GmbH (Germany), Sonja Schimmler – Fraunhofer FOKUS & TU Berlin (Germany), Stefan Dietze – GESIS & Heinrich-Heine University (Germany) and Frank Krüger – Wismar University of Applied Sciences (Germany)
Website: https://nfdi4ds.github.io/nslp2024/
Scientific research is almost exclusively published in unstructured text formats, which are not readily machine-readable. While technological approaches can help to get this flood of scientific information and new knowledge under control, the development of such technologies is very complex in practice and hinders the creation of infrastructures and systems to track research and assist the scientific community with applications such as dedicated scientific search engines and recommender systems. The Workshop on Natural Scientific Language Processing and Research Knowledge Graphs aims to bring together researchers working on the processing, analysis, transformation and making-use-of scientific language including all relevant sub-topics with a special focus on RKGs.
D2R2’24: Third International Workshop on Linked Data-driven Resilience Research 2024
Organizers: Sebastian Tramp – eccenca GmbH (Germany), Julia Holze – InfAI e.V. (Germany), Ricardo Usbeck – Leuphana University Lüneburg (Germany) and Sören Auer – TIB (Germany)
Website: https://d2r2.aksw.org/
In the face of continuously changing contextual conditions and ubiquitous disruptive crisis events, the concept of resilience refers to some of the most urgent, challenging, and interesting issues of nowadays society. Recent crises like the Covid-19 pandemic wave, the Russia-Ukraine War or the energy crisis have not only tested supply chains and economic value networks to their limits but revealed the need to increase flexibility of technical infrastructures, energy supply, health systems, and social textures alike. Currently, many economic and social spheres are continuously challenged by recession fear, political ploys, and weather disasters to unfold capacities to withstand as well as refine and transform themselves to stay ahead of changes. Semantically represented data together with emerging technologies such as LLMs and agents can play a crucial role in increasing transparency of value chains and understanding the complex mechanisms of crisis factors on a global level. The systematic integration, KI-based modelling and analysis of huge amounts of data from various sources can build a new basis for situational awareness and decision making as well as for the elaboration of advanced resilience strategies. The D2R2’24 workshop, which is again organised by the CoyPu project (https://coypu.org/), will provide an open forum to exchange current issues, ideas, and trends in the area of Data-driven Resilience Research. The workshop will bring together scientists, software engineers, resilience practitioners, and domain experts in order to approach the topic from a multi-disciplinary perspective. Ongoing technological developments, current research approaches as well as use case scenarios, and field reports will be presented and discussed with a broad specialist audience. We invite contributions of novel results and ongoing work as well as position papers focusing on various aspects of Data-driven Resilience Research from a scientific or practical perspective.
Second Workshop on Semantic Technologies and Deep Learning Models for Scientific, Technical and Legal Data
Organizers: Rima Dessi – FIZ Karlsruhe (Germany), Hidir Aras – FIZ Karlsruhe (Germany), Danilo Dessi – GESIS (Germany) and Francesco Osborne – The Open University (United Kingdom)
Website: https://semtech4stld.github.io/
The rapid growth of online available scientific, technical, and legal data such as patents, reports, articles, etc. has made the large-scale analysis and processing of such documents a crucial task. Today, professionals (e.g., scientists, patent experts, lawyers, etc.) contribute to this data every day. It is a challenging task to process, analyze, and explore these documents due to their length, the use of domain-specific vocabulary, and the complexity introduced by targeting various scientific fields and domains. These documents are semi-structured and cover unstructured textual parts as well as structured parts such as tables, mathematical formulas, diagrams, and domain-specific information such as chemical names, bio-sequences, etc. Such kind of information brings complexity in processing such documents; however, data is the lifeblood of many applications, and its preservation, analysis, enrichment, and use are key for applications in several domains. To address the challenges mentioned above, Semantic Web Technologies, Natural Language Processing (NLP) techniques, and Deep Neural Networks (DNN) must be leveraged in order to provide efficient and effective solutions for creating easily accessible and machine-understandable knowledge for such data. This workshop aims to provide a meeting forum for people from academia as well as industry to come together and discuss topics such as the application of Semantic Web Technologies and Deep Learning Models to scientific, technical, and legal data. Further, the primary objective of the workshop is to promote collaboration among the participants and exchange ideas.
GEOLD 2024: 6th Geospatial Linked Data Workshop
Organizers: Timo Homburg – i3main & Mainz University of Applied Sciences (Germany), Beyza Yaman – Trinity College (Ireland), Mohamed Ahmed Sherif – University of Paderborn (Germany) and Axel-Cyrille Ngonga Ngomo – University of Paderborn (Germany)
Website: https://i3mainz.github.io/GeoLD2024/
Geospatial data are essential not only for many traditional GIS tasks such as navigation, logistics, and tourism, but even more for emerging technologies like autonomous vehicle navigation, smart city technologies, and further location-based services. For all these technologies, geospatial linked data (GLD) is a crucially important source of machine-readable pre-interpreted information. Recently, we can observe a transformation process of spatial data infrastructures from previously merely acting as data providers to becoming brokers of geospatial information of different kinds, origins, quality, and a need to interconnect and incorporate information from different data repositories, often even in real-time. This need for GLD integration leads to efforts to create next-generation knowledge graphs which integrate multiple spatial datasets with large numbers of general datasets containing some geospatial references (e.g., DBpedia, Wikidata) and even volunteered geographic information (e.g., LinkedGeoData) and sensor data. This integration, either on the public Web or within organizations has immense socio-economic and academic benefits. The upsurge in linked data-related presentations in the Eurogeographics data quality workshop series, in relevant journal publications, in activities of standardization bodies (OGC GeoSPARQL), and in Spatial Data Applications shows a deep interest in GLD in national mapping agencies and beyond. GLD enables web-based, interoperable geospatial data infrastructures that may enhance and support existing standardization efforts like Europe’s INSPIRE directive. Moreover, geospatial information systems benefit from Linked Data principles in building the next generation of spatial data applications, e.g., federated smart buildings, self-piloted vehicles, delivery drones, or automated local authority services, which is of increasing interest to various stakeholders. This workshop invites papers covering the challenges and solutions for handling GLD, especially for building high-quality, adaptable, geospatial data infrastructures and next-generation spatial applications. We aim to demonstrate the latest approaches and implementations and to discuss the solutions to challenges and issues arising from research and industrial organizations.
Semantic Methods for Events and Stories (SEMMES)
Organizers: Pasquale Lisena – EURECOM (France), Simon Gottschalk – Leibniz Universität Hannover (Germany) and Inès Blin – Sony Computer Science Laboratories-Paris (France) & Vrije University Amsterdam (Netherlands)
Website: https://anr-kflow.github.io/semmes/
An important part of human history and knowledge is made of events, which can be aggregated and connected to create stories, be they real or fictional. These events as well as the stories created from them can typically be inherently complex, reflect societal or political stances and be perceived differently across the world population. The Semantic Web offers technologies and methods to represent these events and stories, as well as to interpret the knowledge encoded into graphs and use it for different applications, spanning from narrative understanding and generation to fact-checking. The aim of SEMMES is to offer an opportunity to discuss the challenges related to dealing with events and stories, and how we can use semantic methods to tackle them. We welcome approaches which combine data, methods and technologies coming from the Semantic Web with methods from other fields, including machine learning, narratology or information extraction. This workshop wants to bring together researchers working on complementary topics, in order to foster collaboration and sharing of expertise in the context of events and stories.
7th International Workshop on Semantic Web solutions for large-scale biomedical data analytics (SeWeBMeDA-2024)
Organizers: Ali Hasnain – Royal College of Surgeons (Ireland), Michel Dumontier – Maastricht University (Netherlands), Dietrich Rebholz-Schuhmann – ZB MED Centre for Life Sciences (Germany) and Alba Catalina Morales Tirado – The Open University (United Kingdom)
Website: https://sites.google.com/view/sewebmeda-2024/
The life sciences domain has been an early adopter of linked data and a consider- able portion of the Linked Open Data cloud is composed of life sciences data sets. The deluge of in-flowing biomedical data, partially driven by high-throughput gene sequencing technologies, is a key contributor to these developments. The available datasets require integration according to international standards, large-scale distributed infrastructures, specific techniques for data access, and offer data analytics benefits for decision support. With Semantic Web and Linked Data technologies, the promise to enable the processing of large as well as semantically heterogeneous data sources for capturing new knowledge becomes easier. In this workshop, we invite papers for life sciences and biomedical data processing with the amalgamation of Linked Data and Semantic Web technologies for better data analytics, knowledge discovery and user-targeted applications. The submitted research should aim to provide novel contributions to Knowledge Acquisition in the research community as well as the working Data Scientist. We consider SeWeBMeDA a successfully established workshop, and this year will be its seventh edition.
Workshop on Actionable Knowledge Representation and Reasoning for Robots (AKR^3)
Organizers: Philipp Cimiano – Bielefeld University (Germany), Michael Beetz – Bremen University (Germany), Enrico Motta – The Open University (United Kingdom), Ilaria Tiddi – Vrije University Amsterdam (Netherlands), Michaela Kümpel – Bremen University (Germany) and Jan-Philipp Töberg – Bielefeld University (Germany)
Website: https://kr3-workshop.net/
We propose a novel workshop on the topic of how robots can be endowed with the ability to perform common sense reasoning in order to make sense of their environment as well as plan and parameterize their actions. The workshop focuses in particular on home environments where robots need to carry out daily tasks such as cleaning, setting the table, preparing meals etc. Current robots are challenged by the dynamic nature of these environments, which requires them to deal with new situations, requests, tasks, objects and goals they might not have direct experience with. As robots can not be pre-programmed for all possible situations, tasks and objects, it is an important question to investigate how they can be equipped with the ability to acquire and apply common sense knowledge to improve their sensemaking capabilities and reason about how tasks should be executed. Potentially, this can lead to robots that are more versatile and flexible, as they can tackle novel situations through reasoning instead of having to be retrained. Given the availability of many common sense knowledge resources on the Web and the ability of large language models to extract and generate knowledge, this is a timely research topic. Our workshop will combine classical workshop elements (presentation of contributed papers, invited speaker) with tutorials that provide hands-on examples of how symbolic common sense knowledge can be put into action in existing robot architectures (in particular the cognitive robot abstract machine CRAM).
First International Workshop on Generative Neuro-Symbolic AI (GeNeSy 2024).
Organizers: Jacopo de Berardinis – King’s College London (United Kingdom), Nitisha Jain – King’s College London (United Kingdom), Jongmo Kim – King’s College London (United Kingdom) and Filip Ilievski – Vrije University Amsterdam (Netherlands)
Website: https://sites.google.com/view/genesy2024/
Generative AI is revolutionising our society by enabling innovative applications in art, language, healthcare, and more, fundamentally transforming the way we create, communicate, and solve complex problems. This sentence was indeed written by a large language model (LLM) – currently one of the most popular neural approaches that is trained to produce outputs through a sequence modelling objective. LLMs are trained to generate outputs that are statistically plausible, realistic, but not necessarily correct. As such, while the language models can generate fluent text and mimic humans on many tasks, trusting their reasoning is hindered by challenges such as coherence, consistency, and explainability. Meanwhile, Symbolic AI provides sound and well-understood formal reasoning and explanation via knowledge representation that can be inspected to interpret how decisions are made from data, while lacking flexible generalisation to novel inputs. Neuro-Symbolic (NeSy) AI aims to build rich computational AI models, systems and applications by combining neural and symbolic learning and reasoning. It hopes to create synergies among the strengths of neural and symbolic AI while overcoming their complementary weaknesses. The GeNeSy workshop aims at gathering researchers in Generative and Neuro-Symbolic AI to combine expertise, perspectives, and pioneering works and pave the way towards novel methods and paradigms for Generative Neuro-Symbolic AI. GeNeSy will feature novel and already published papers on NeSy methods for reasoning and explanations in multiple modalities, benchmarks and evaluation methods, challenges like commonsense reasoning and human-AI teaming, and reflection on ethical and social implications of GenAI. To the best of our knowledge, GeNeSy is the first Semantic Web workshop that brings ideas from NeSy and GenAI together, enabling discussions between these two communities and facilitating impact on the future development of AI.
DQMLKG – Data Quality meets Machine Learning and Knowledge Graphs: Bridging Precision with Intelligence
Organizers: Anisa Rula – University of Brescia (Italy), Maria Angela Pellegrino – University of Salerno (Italy), Michael Cochez – Vrije University Amsterdam (Netherlands), Jose Emilio Labra Gayo – University of Oviedo (Spain) and Mehwish Alam – Institut Polytechnique de Paris (France)
Website: https://dqmlkg.github.io/
Machine Learning (ML) and Knowledge Graphs (KGs) possess a symbiotic relationship with the potential to mutually enhance their capabilities. ML can play a pivotal role in the construction of KGs by automating ontology design, inferring classes and relations from alternative sources, and aiding data curators in making informed decisions. ML algorithms need data to be in a “certain form”, meaning that they need to get the data prepared and ensure high-quality data used as input. Poor-quality datasets can lead to biased or inaccurate ML models. Conversely, KGs can enrich ML models through node or graph embedding techniques, link prediction, supporting explainability and improving the overall performance of data-driven models. This workshop aims to explore the intricate interplay of data quality, ML, and KGs, elucidating limitations in assessment methodologies, proposing effective methods for objective quality assessment, and addressing challenges on ML and Artificial Intelligence (AI) in general, verify if and to what extent well-known quality metrics are compliant with ML-based quality assessment, and addressing FAIR principles. We also welcome proposals riding the path of Explainable AI, Large Language Models, Generative AI, and any AI-driven approach that can be applied to the Semantic Web technologies to support and enhance data quality assessment and improvement.
Tutorials
Semantic Data Enrichment: from Interactive Exploration to Scalable Deployment
Presenter: Matteo Palmonari – University of Milano-Bicocca (Italy), Flavio De Paoli – University of Milano-Bicocca (Italy), Dumitru Roman – University of Milano-Bicocca (Italy) and Roberto Avogadro – University of Milano-Bicocca (Italy)
Website: https://enrichmydata.github.io/eswc2024-tutorial
This tutorial introduces the topic of semantic data enrichment, covering theoretical and practical considerations. In particular, the tutorial will provide an explanation of the role that semantics play in data enrichment for downstream AI-based applications, a review of the advantages and limitations of tools, methodologies and techniques for semantic data enrichment available today, and a practical dive into the creation of data transformations for enriching the data.
Contextualizing and Executing Robot Manipulation Plans Using Web Knowledge
Organizers: Philipp Cimiano – Bielefeld University (Germany), Michael Beetz – Bremen University (Germany), Enrico Motta – The Open University (United Kingdom), Ilaria Tiddi – Vrije University Amsterdam (Netherlands), Michaela Kümpel – Bremen University (Germany) and Jan-Philipp Töberg – Bielefeld University (Germany)
Website: https://kr3-workshop.net/