A5008517596- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Service-Oriented Architecture and Web Services
- Topic Modeling
- Data Quality and Management
- Advanced Database Systems and Queries
- Culinary Culture and Tourism
- Robotics and Automated Systems
- Modular Robots and Swarm Intelligence
- Social Robot Interaction and HRI
- Advanced Graph Neural Networks
- Scientific Computing and Data Management
- Digital and Traditional Archives Management
- Context-Aware Activity Recognition Systems
- Library Science and Information Systems
- Data Mining Algorithms and Applications
- 3D Surveying and Cultural Heritage
- Video Analysis and Summarization
- Multi-Agent Systems and Negotiation
- Music and Audio Processing
- Cultural Heritage Management and Preservation
- Mobile Crowdsensing and Crowdsourcing
- Digital and Cyber Forensics
- Big Data Technologies and Applications
University of Bologna
2016-2024
Zambon (Italy)
2021-2024
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo"
2016-2022
Technische Informationsbibliothek (TIB)
2021
Data Management (Italy)
2021
Open Knowledge (United Kingdom)
2021
Università Cattolica del Sacro Cuore
2021
National Research Council
2016-2019
Digital archives of memory institutions are typically concerned with the cataloguing artefacts artistic, historical, and cultural value. Recently, new forms citizen participation in heritage have emerged, producing a wealth material spanning from visitors’ experiential feedback on exhibitions to digitally mediated interactions like ones happening social media platforms. Citizen curation is proposed context European project SPICE (Social Participation, Cohesion, Inclusion through Cultural...
Data integration is the dominant use case for RDF Knowledge Graphs. However, Web resources come in formats with weak semantics (for example, CSV and JSON), or specific to a given application BibTex, HTML, Markdown). To solve this problem, Graph Construction (KGC) gaining momentum due its focus on supporting users transforming data into RDF. using existing KGC frameworks result complex processing pipelines, which mix structural semantic mappings, whose development maintenance constitute...
Luigi Asprino, Luana Bulla, Stefano De Giorgis, Aldo Gangemi, Ludovica Marinucci, Misael Mongiovi. Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Architectures. 2022.
Creative influence is responsible for a considerable part of the creative process an artist and can largely be associated with their social circle. It has been observed that type amount relationships other fellow artists correlates success artist. Most recent literature focused on using artefact similarity as proxy between two artists. However, this approach neglects significance artist’s network. In work, we rely ontology comprehensively model relationship individuals Knowledge Graph design...
Linked Open Data (LOD) is the largest, collaborative, distributed, and publicly-accessible Knowledge Graph (KG) uniformly encoded in Resource Description Framework (RDF) formally represented according to semantics of Web Ontology Language (OWL). LOD provides researchers with a unique opportunity study knowledge engineering as an empirical science: observe existing modelling practices possibly understanding how improve methodologies representation formalisms. Following this perspective,...
The Web and its Semantic extension (i.e. Linked Open Data) contain open global-scale knowledge make it available to potentially intelligent machines that want benefit from it. Nevertheless, most of Data lack ontological distinctions have sparse axiomatisation. For example, such as whether an entity is inherently a class or individual, physical object not, are hardly expressed in the data, although they been largely studied formalised by foundational ontologies (e.g. DOLCE, SUMO). These...
World modelling, i.e. building a representation of the rules that govern world so as to predict its evolution, is an essential ability for any agent interacting with physical world. Recent applications Transformer architecture problem modelling from video input show notable improvements in sample efficiency. However, existing approaches tend work only at image level thus disregarding environment composed objects each other. In this paper, we propose combining Transformers slot-attention...
In this paper we describe and evaluate a VR application, designed with novel approach that allows personalized interaction more immersive virtual experience. This system uses both user-based methodology in which the user expresses his/her emotions by interacting directly environment; an artificial intelligence-driven is based on automated language systems able to detect emotion moral values from verbal speech. study evaluated usability immersivity of our sample 30 museum visitors. The...
Mapping complex structured data to RDF, e.g. for the creation of linked data, requires a clear understanding but also paradigm used by mapping tool. We illustrate this with an empirical study comparing two different tools, in particular considering likelihood user error. One tool uses path descriptions, JSONPath or XPath, access elements; other default triplification which can be queried, SPARQL. As example former, YARRRML, map from CSV, JSON and XML RDF. latter, extension SPARQL, SPARQL...
This article explores and presents innovative methods technologies for supporting citizen curation of cultural heritage. Relevant outcomes the SPICE project (Social Participation, Cohesion, Inclusion through Cultural Engagement) are presented, focusing on enhancing state content management delivery strategies in museums memory institutions. We argue that requires a principled way managing integrating responses, contributions, data flows domain heritage, raising challenges opportunities such...
Citizen curation is gaining momentum as a new form of engagement with cultural heritage. curatorial activities require and produce wealth information, ranging from descriptions the artefacts to visitor experience feedback. Although formalising integrating such various data paramount importance, domain lacks comprehensive ontologies enable querying, interpreting reasoning over collected data. SPICE - Social Participation, Cohesion, Inclusion through Cultural Engagement an EU project dedicated...
The need of handling semantic heterogeneity resources is a key problem the Semantic Web. State art techniques for ontology matching are technology addressing this issue. However, they only partially exploit natural lan- guage descriptions entities and mostly unable to find correspondences between having dif- ferent logical types (e.g. mapping properties classes). We introduce novel approach aimed at finding according intensional mean- ing their models, hence abstracting from types. Lexical...