November 11, 2024
8:00 AM ET
9:00 AM ET
10:40 AM ET
3:40 PM ET
9:00 AM ET
8:00 AM ET
Session Chair: Gianluca Demartini
Many challenging data integration problems, in particular in data journalism, feature heterogeneity at the level of the schema and the data model. To overcome the heterogeneity, we have shown how data of many (semi)structured models can be converted in fine-granularity graphs, enriched and densified with the help of information extraction. Such fine-grained graphs, however, are hard to grasp for non-technical users. To help them get acquainted with a dataset, we devised an abstraction method, which identifies, in fine-granularity data graphs, structured objects endowed with an internal structure, and relationships between them. Given a semistructured dataset, we automatically produce an Entity-Relationship style diagram; in contrast with traditional E-R models, our entities may feature deep nesting, reflecting the nested and possibly recursive structure present in some data models. We thus obtain an automated way of “rescuing” the conceptual model, which we argue is best viewed as a graph, behind any application dataset. We then describe automatic techniques for finding the most interesting paths connecting entities in a dataset.
Session Chair: Gong Cheng
Quality in Color: Using Knowledge Graphs for Enhanced Quality Control in an Automotive Paintshop — Bram Steenwinckel, Colin Soete, Pieter Moens, Joris Mussche, Sofie Van Hoecke and Femke Ongenae [In-Use]
✪ Intelligent Urban Traffic Management via Semantic Interoperability across Multiple Heterogeneous Mobility Data Sources — Mario Scrocca, Marco Grassi, Marco Comerio, Valentina Anita Carriero, Tiago Delgado Dias, Ana Vieira Da Silva and Irene Celino [In-Use]
✪ KROWN: A Benchmark for RDF Graph Materialisation — Dylan Van Assche, David Chaves-Fraga and Anastasia Dimou [Resource]
✪ BLINK: Blank Node Matching Using Embeddings — Alexander Becker, Mohamed Ahmed Sherif and Axel-Cyrille Ngonga Ngomo [Research]
Session Chairs: Paul Groth, Valentina Tamma, Jan-Christoph Kalo
Session Chair: Vanessa Lopez
A Benchmark Knowledge Graph of Driving Scenes for Knowledge Completion Tasks — Ruwan Wickramarachchi, Cory Henson and Amit Sheth
Beyond generic skills: creating-capability centric, company-specific knowledge graphs from job descriptions — Henri Egle Sorotos, Kaan Karakeben and Ahmad Assaf
openCypher Queries over Combined RDF and LPG Data in Amazon Neptune — Willem Broekema, Mohamed Elzarei, Ora Lassila, Carlos Manuel Lopez Enriquez, Marcin Neyman, Florian Schmedding, Michael Schmidt, Andreas Steigmiller, Geo Varkey, Gregory Todd Williams and Amanda Xiang
Integrating system design information using a self-defining ontology — Stephen Hookway and William Norsworthy Jr.
Session Chair: Lise Stork
AdaptLIL: A Real-Time Adaptive Linked Indented List Visualization for Ontology Mapping — Bo Fu and Nicholas Chow [Research]
✪ Developing Application Profiles for Enhancing Data and Workflows in Cultural Heritage Digitisation Processes — Sebastian Barzaghi, Ivan Heibi, Arianna Moretti and Silvio Peroni [In-Use]
Diachronical geometry without polygons: the extended HHT ontology for heterogeneous geometrical representations — William Charles, Nathalie Aussenac-Gilles and Nathalie Hernandez [Resource]
Repairing Networks of EL⊥ Ontologies using Weakening and Completing — Ying Li and Patrick Lambrix [Research]
Session Chairs: Paul Groth, Valentina Tamma, Jan-Christoph Kalo
Session Chair: Matteo Palmonari
Advancing Robotic Perception with Perceived-Entity Linking — Mark Adamik, Romana Pernisch, Stefan Schlobach and Ilaria Tiddi [Research]
Exploiting Distant Supervision to Learn Semantic Descriptions of Tables with Overlapping Data — Binh Vu, Craig Knoblock, Basel Shbita and Fandel Lin [Research]
Knowledge Graphs for Enhancing Large Language Models in Entity Disambiguation — Gerard Pons, Besim Bilalli and Anna Queralt [Research]
UFEL: a By-design Understandable and Frugal Entity Linking System for French Microposts — Vivien Leonard, Béatrice Markhoff and Jean-Yves Antoine [In-Use]
Session Chairs: Paul Groth, Valentina Tamma, Jan-Christoph Kalo
Session Chair: Tim Finin
We are amid three revolutions in AI: deep learning, knowledge graphs, and automated reasoning, as articulated by Prof. Kenneth Forbus during the AI Session at the National Science Board Meeting on May 1, 2024. Technology in each of these areas has progressed to the extent that it is used daily and is delivering significant value. While deep learning, which has unleashed powerful tools like ChatGPT is a large focus of today’s AI, knowledge graphs and reasoning are complements to deep learning. Knowledge graphs have already been powering key web and e-commerce services provided by large corporations. Automated reasoning techniques are in wide use in many areas—for example, in the auto industry to find flaws in its electrical systems and verify behavior with respect to design specifications.
In this talk, we will discuss techniques, technologies, and strategies for building out the knowledge infrastructure that will be essential and necessary to support the next generation of AI. The National Science Foundation’s Open Knowledge Network (OKN), envisioned as part of NSFs Harnessing the Data Revolution Big Idea, provides an important start. The Prototype-OKN (https://www.proto-okn.net/) is a coordinated effort among 18 projects funded under the NSF Proto-OKN project, in collaboration with NASA, NIH, NIJ, NOAA, USGS and other agencies, to create an open knowledge network structure linking disparate, heterogenous information from diverse sources. Of these, 15 projects are “Theme 1” efforts focused on providing solutions for specific problems working in conjunction with federal, state or other government agencies. Two projects—FRINK and SPIDER—are working towards providing a common Proto-OKN “fabric”, or technical infrastructure, to deploy Theme 1 solutions, and one project—EduGate—focusing on the education, training, and outreach for this effort.
Knowledge representation and reasoning are not new topics in Computer Science. However, to make translational impact in real-world applications we need to make a shift towards treating the development and operation of computer science-based knowledge structures as infrastructure—in addition to just bespoke solutions to specific problems. This would begin with the hosting of repositories of knowledge in computational form based on open-source government, science, and other open data. The term “translational” implies focus on use-inspired, solution-oriented R&D efforts with the potential to directly impact people’s everyday lives. An important focus is on education and training and teaching of knowledge representation at every level from high school to computer science undergraduates, and above. A key consideration is to pay attention to issues from governance to ethics to help build trust in the system.
Session Chair: Angelo Salatino
Knowledge Graph-Driven Neuro-Symbolic System for Intelligent Document Matching — Jans Aasman
Causal Knowledge Graph for Scene Understanding in Autonomous Driving — Utkarshani Jaimini, Cory Henson and Amit Sheth
Knowledge Representation and Engineering for Smart Diagnosis of Cyber Physical Systems — Ameneh Naghdipour, Benno Kruit, Jieying Chen, Peter Kruizinga, Godfried Webers and Stefan Schlobach
Assessing the Economic Impact of the 2024 Baltimore Bridge Collapse using RDF/OWL to Crosswalk the NAICS, SICS and GICS Industry Classification Systems — Christopher Carrino
Session Chair: Peter Haase
CRAWD: Sampling-Based Estimation of Count-Distinct SPARQL Queries — Thi Hoang Thi Pham, Pascal Molli, Brice Nédelec, Hala Skaf-Molli and Julien Aimonier-Davat [Research]
✪ PathFinder: Returning Paths in Graph Queries — Benjamin Farias, Wim Martens, Carlos Rojas and Domagoj Vrgoc [Research]
eSPARQL: Representing and Reconciling Agnostic and Atheistic Beliefs in RDF-star knowledge graphs — Xinyi Pan, Daniel Hernandez, Philipp Seifer, Ralf Lämmel and Steffen Staab [Research]
Finally understanding SPARQL queries, are we there already? – Multilingual Natural-Language Representations of SPARQL queries via LLMs — Aleksandr Perevalov, Aleksandr Gashkov, Maria Eltsova and Andreas Both [Research]
Session Chair: Simon Razniewski
Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data — Antonio De Santis, Marco Balduini, Federico De Santis, Andrea Proia, Arsenio Leo, Marco Brambilla and Emanuele Della Valle [In-Use]
DISCIE – Discriminative Closed Information Extraction — Cedric Möller and Ricardo Usbeck [Research]
InstructIE: A Bilingual Instruction-based Information Extraction Dataset — Gui Honghao, Qiao Shuofei, Ye Hongbin, Sun Mengshu, Liang Lei, Jeff Z. Pan, Chen Huajun and Zhang Ningyu [Resource]
✪ SciHyp: A Fine-grained Dataset Describing Hypotheses and Their Components from Scientific Articles — Rosni Vasu, Cristina Sarasua and Abraham Bernstein [Resource]
Oscar Corcho, Irene Celino, Annalisa Gentile, Paul Groth
Session Chairs: Juan Sequeda & Sabrina Kirrane
Session Chair: Jennifer D’Souza
Challenge Website: https://sites.google.com/view/llms4ol/
Session Chair: Hala Skaf-Molli
✪ CimpleKG: A Continuously Updated Knowledge Graph on Misinformation, Factors and Fact-Checks — Gregoire Burel, Martino Mensio, Youri Peskine, Raphaël Troncy, Paolo Papotti and Harith Alani [Resource]
Data Privacy Vocabulary – Version 2 — Harshvardhan J. Pandit, Beatriz Esteves, Georg P. Krog, Paul Ryan, Delaram Golpayegani and Julian Flake [Resource]
The ICS-SEC KG: An Integrated Cybersecurity Resource for Industrial Control Systems — Kabul Kurniawan, Elmar Kiesling, Dietmar Winkler and Andreas Ekelhart [Resource]
Do LLMs Really Adapt to Domains? An Ontology Learning Perspective — Huu Tan Mai, Cuong Xuan Chu and Heiko Paulheim [Research]
Session Chair: Ernesto Jimenez-Ruiz
AutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning — Michael Färber, David Lamprecht and Yuni Susanti [Resource]
Knowledge Graph Structure as Prompt: Improving Small Language Models Capabilities for Knowledge-based Causal Discovery — Yuni Susanti and Michael Färber [Research]
SparkKG-ML: A Library to Facilitate end–to–end Large–scale Machine Learning over Knowledge Graphs in Python — Bedirhan Gergin and Charalampos Chelmis [Resource]
Multi-view Transformer-based Network for Prerequisite Learning in Concept Graphs — Zhichun Wang, Yifeng Shao, Boci Peng, Bangqi Li, Yun Li, Qianren Wang and Nijun Li [Research]
The Gala Dinner will be held in the usual Lunch Hall at the Conference Hotel.
Session Chair: Katja Hose
The original idea of the Semantic Web was not just to bring knowledge representation and reasoning to the Web but to make these technologies pervasive in our use of information technology. The idea has matured into modern enterprise knowledge graphs and – according to Gartner – has become a major mainstream trend. Organizations are using knowledge graphs without feeling the need to advertise this fact. However, getting here took a long time,” the original Semantic Web vision was introduced at the tail end of the so-called “AI winter”, and the close relationship with AI greatly slowed its adoption. Now, given the popularity of generative AI, we should re-examine the vision and understand what is the role of AI in the Semantic Web, and what is the role of the Semantic Web in AI.
In this talk I will reflect on the more than a quarter century of work on building the technologies for the Semantic Web and how this work still continues. I will discuss the “wins”, the “losses”, the lessons learned, and describe how I see the future. I believe we are now ready for the next step: to finally realize the original Semantic Web vision, that of agents, planning, and reasoning.
Session Chair: Domagoj Vrgoč
Compiling SHACL into SQL — Maxime Jakubowski and Jan Van den Bussche [Research]
KGHeartBeat: a Knowledge Graph Quality Assessment Tool — Maria Angela Pellegrino, Anisa Rula and Gabriele Tuozzo [Resource]
Supervised Relational Learning with Selective Neighbor Entities for Few-Shot Knowledge Graph Completion — Jiewen Hou, Tianxing Wu, Jingting Wang, Shuang Wang and Guilin Qi [Research]
Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion — Yang Liu, Xiaobin Tian, Zequn Sun and Wei Hu [Research]
Session Chair: François Scharffe
Expanding the Scope: Inductive Knowledge Graph Reasoning with Multi-Starting Progressive Propagation — Zhoutian Shao, Yuanning Cui and Wei Hu [Research]
Numerical Literals in Link Prediction: A Critical Examination of Models and Datasets — Moritz Blum, Basil Ell, Hannes Ill and Philipp Cimiano [Research]
SnapE – Training Snapshot Ensembles of Link Prediction Models — Ali Shaban and Heiko Paulheim [Research]
Unaligned Federated Knowledge Graph Embedding — Deyu Chen, Hong Zhu, Jinguang Gu, Rusi Chen and Meiyi Xie [Research]
Session Chair: Francesco Osborne
Empowering Causal Machine Learning for Large-scale Manufacturing Pipelines with Knowledge Graphs — Yuxin Zi, Cory Henson and Amit Sheth
Explainability of Quality Issues in Manufacturing: a Semantic Based Approach — Léa Charbonnier, Franco Giustozzi, Julien Saunier and Cecilia Zanni-Merk
Causal Neuro-Symbolic AI for Root Cause Analysis in Smart Manufacturing — Utkarshani Jaimini, Cory Henson, Amit Sheth and Ramy Harik
Session Chair: Anna Lisa Gentile
Distilling Event Sequence Knowledge From Large Language Models — Somin Wadhwa, Oktie Hassanzadeh, Debarun Bhattacharjya, Ken Barker and Jian Ni [Research]
Increasing the Accuracy of LLM Question-Answering Systems on SQL Databases with Ontologies — Juan F. Sequeda and Dean Allemang [In-Use]
PreAdapter: Pre-training Language Models on Knowledge Graphs — Janna Omeliyanenko, Andreas Hotho and Daniel Schlör [Research]
PRONTO: Prompt-based Detection of Semantic Containment Patterns in MLMs — Alessandro De Bellis, Vito Walter Anelli, Tommaso Di Noia and Eugenio Di Sciascio [Research]
Session Chair: Milan Markovic
✪ Semantic and technically interoperable data exchange in the Flanders Smart Data Space — Dwight Van Lancker, Steven Logghe, Julian Andres Rojas, Annelies De Craene, Ziggy Vanlishout and Pieter Colpaert [In-Use]
✪ Relationships are Complicated! An Analysis of Relationships Between Datasets on the Web — Kate Lin, Tarfah Alrashed and Natasha Noy [Research]
DUNKS: Chunking and Summarizing Large and Heterogeneous Data for Dataset Search — Qiaosheng Chen, Xiao Zhou, Zhiyang Zhang and Gong Cheng [Research]
Leveraging Knowledge Graphs for Earth System Dataset Discovery — Vincent Armant, Felipe Vargas-Rojas, Victoria Agazzi, Jean-Christophe Desconnets, Isabelle Mougenot, Valentina Beretta, Stephane Debard, Danai Symeonidou, Amira Mouakher, Joris Guérin, Thibault Catry and Emmanuel Roux [In-Use]