The following projects were accepted to and participated in the ESWC 2022 Projects Networking Session:
The CLEOPATRA project is a Marie Skłodowska-Curie Innovative Training Network. Its main objective is to explore multilingual methods to analyse and understand how major events that influence and shape our lives and societies extracting, processing and validating information from media texts.
The Cleopatra project encompasses a great variety of problems from multilingual language processing to event-centric cross-lingual analysis and cross-cultural studies, which requires the development of new technologies, algorithms and systems resulting in outputs leading to facilitation of innovative products and services within the Cleopatra network and beyond.
D2KAB is a 4.5-year French ANR research project which primary objective is to create a framework to turn agronomy and biodiversity data into knowledge –semantically described, interoperable, actionable, open– and investigate scientific methods and tools to exploit this knowledge for applications in science & agriculture. D2KAB develops and maintain the AgroPortal ontology repository.
The Drugs4COVID project started in September 2020, and has a duration of 24 months, finishing in August 2022. It was born from the results obtained from two Hackathons that took place during the worst times of the pandemic. These events brought together the combined knowledge of the different profiles in our research group to create a resource that, from automated knowledge extraction of biomedical texts (CORD-19), we built a Knowledge Graph with COVID-19-related information with the objective of having a knowledge base that can be exploited to discover new drugs that could serve to treat COVID-19 in situations of drug shortages.
European Database for Multiscale Modelling of Radiation Damage (ENTENTE)
The safe long term operation of nuclear power plants relies on the implementation of ageing management programmes, amongst other actions. There are multiple structures, systems and components included on ageing management programmes of which ENTENTE focuses on the ageing management and integrity assessment of the reactor pressure vessel.
Objective: Capitalise and exploit these data at best, for the benefit of reactor pressure vessel ageing management programmes, by using modern and innovative data collection and management’s tools. All data produced within ENTENTE will be collected and stored according to FAIR (Findability, Accessibility, Interoperability, and Reusability) principles with proper ontologies.
Website: not yet available
FAIR-IMPACT is a new Horizon Europe Coordinated Support Action project in the EOSC roadmap starting in June 2022 for 3 year. The project aims is to enable the implementation of the FAIR principles for the EOSC across scientific domains and research outputs.
The ImProVIT (Transforming big data into knowledge: for deep immune profiling in vaccination, infectious diseases, and transplantation) project started in Oct 2019 and runs until August 2023. Every human has the same immune system components, but these components’ regulations vary from human to human. Understanding the human body’s immune response to different medical conditions is crucial. This requires seamless integration of an enormous amount of diverse and fine-grained data from various medical use cases. The project focuses on developing a shared understanding of the human immune system. This project aims at integrating heterogeneous data sets with knowledge encoded in biomedical ontologies and open source databases into a knowledge‐driven framework. The ImProVIT KG increases the understanding of the human immune system; it also provides the basis to evaluate factors playing a role in vaccine response, infectious diseases, and transplant rejection. The ImProVIT project is fully supported by the Lower Saxony Ministry of Science and Culture, Germany.
Knowledge Graphs at Scale — ‘KnowGraphs’
Knowledge graphs (KGs) is a Marie Skłodowska-Curie H2020 project funded by the European Commission.
The objective of KnowGraphs is to scale KGs to be accessible to a wide audience of users across multiple domains including companies (in domains including Industry 4.0, bio-medicine, finance, law) of all sizes and even end users (e.g., through personal assistants and web search). Addressing this goal demands a mix of works from the theoretical foundations to the exploitation and economic repercussions of knowledge graphs. KnowGraphs focuses on addressing four of the facets of KG management: representation, construction and maintenance, operation and exploitation.
ONTOLOGY-BASED DECENTRALIZED SHARING OF INDUSTRY DATA
IN THE EUROPEAN CIRCULAR ECONOMY
Semantic interoperability of data is one of the biggest barriers towards data sharing in the Circular Economy (CE). This three year project provides the technical foundations for information flows that will transform European Industry towards a CE, by means of digitalisation and data sharing. The project leverages open standards for semantic data interoperability in establishing a shared vocabulary, i.e. a network of ontologies for data documentation, as well as a decentralized digital platform that enables collaboration in a secure and privacy-preserving manner. What this project will develop is at its basis a technology for allowing data sharing about materials and products at a global scale. The project will start on June 1st 2022, duration 36 months, EU-funded with 11 partners from 6 countries.
PLATOON (Digital PLAtform and analytic TOOls for eNergy)
PLATOON is an EU-funded H2020 project that aims to digitalize the energy sector, enabling thus data exchange while ensuring privacy and sovereignty. PLATOON knowledge graphs integrate energy data sources in terms of the common understanding of the energy domain stated by the PLATOON Semantic Data Models. The PLATOON framework is validated in seven pilots from four countries.
Policy Enabled Next geNeration Internet (PENNI)
The Policy Enabled Next geNeration Internet (PENNI) project will lay the technical foundations for a policy, trust and transparency enabled decentralised Next Generation Internet (NGI), that can support intelligent agents that act on behalf of humans. Our hypothesis being that decentralized applications that are able to understand constraints, in the form of goals, preferences, norms and usage restrictions, together with trust and transparency mechanisms will give humans more control over how their data is utilised and will foster trustworthiness in NGI applications, such as intelligent agents and devices.
Repurposing of Resources: from Everyday Problem Solving to Crisis Management
Repurposing arises in several situations and domains, from finding substitutes for ingredients in cooking to handling unprecedented situations needing crisis management. Repurposing also offers some exciting challenges for AI, and could offer some valuable case studies for natural language processing, machine learning, knowledge representation and reasoning, in particular for commonsense reasoning, and knowledge graphs. So far we have investigated the challenges of repurposing, we have defined its key concepts, and we have identified some general approaches for solving the problem (pattern analysis, property analysis, mechanistic analysis). Although we have not produced any solutions yet, we have set out a general methodology and we have started developing a general theory, which could serve as a starting point for developing domain-specific solutions for a problem that exists in several different domains.
The growing European data economy requires innovative methods to overcome the existing data-sharing barriers, such as complex and time-consuming consent/contract processes, which currently obstruct the build-up of innovative services that utilize data from multiple data providers. SmashHit project aims to provide a trusted, secure and integrated privacy-by-design reference framework to simplify the consent/contract processes across multiple parties, as well as to enable consent/contract tracing and sharing among multiple data platforms. In addition, smashHit will offer solutions to support data processors in creating legally binding contracts. Furthermore, smashHit will provide methods for data re-identification in case of data leakage and unauthorized use.
TrustKG is a framework for knowledge graphs based on semantic data integration, representation, and curation of Scientific data to enable trustable and interpretable knowledge exploration and discovery. TrustKG aim at enabling interpretable data integration in pipelines for transforming scientific data into semantically rich and linked knowledge graphs. TrustKG will be equipped with computational logic and ontologies to express temporality and causation relationships among ingested, curated, and integrated data. Further, TrustKG methods will resort to experts’ wisdom and computational techniques for validating and explaining data management decisions and outcomes.
Visual Queries in Distributed Knowledge Graphs
The project aims to develop and validate methods for creation and management of visual and multi-modal rich data queries over standalone and distributed knowledge graphs by data professionals and lay users.
The principal objectives of the project involve:
– Developing a concept of rich visual query over RDF data (including user friendly visual and interactive notation), involving also option of visual presentation of existing SPARQL queries;
– Investigating and developing means for rich end-user action in data structure exploration and query creation by integrating the visual query creation paradigm with visual data structure exploration and specification of queries in natural language;
– Providing methods for analysis (including data schema extraction) of practical real-world RDF data endpoints, including custom solutions for exploring and visual querying DBPedia and wikidata (involving context-sensitive auto-completion support) and means for distributed query creation.”