Current Projects
-
Exascale volumes of diverse data from distributed sources are continuously produced. Healthcare data stand out in the size produced (production is expected to be over 2000 exabytes in 2020), heterogeneity (many media, acquisition methods), included knowledge (e.g. diagnosis) and commercial value. The supervised nature of deep learning models requires large labeled, annotated data, which precludes models to extract knowledge and value. Examode solves this by allowing easy & fast, weakly supervised knowledge discovery of exascale heterogeneous data, limiting human interaction.
We are leader of the "Semantic knowledge discovery and visualisation" WP.
The main goals of the WP are:- Develop relation extraction methods to automatically extract semantic relationships between authoritative concepts within un/semi-structured text.
- Leverage entity linking methods in conjunction with developed relation extraction techniques to create report-level semantic networks out of extracted concepts and relationships.
- Model report-level semantic networks through conceptual descriptive frameworks to empower data management and exploitation.
- Develop information retrieval methods to semantically connect and discover semantic networks associated with relevant medical reports.
- Develop information visualization and visual analytics methods for interacting with deep learning algorithm and improve their understandability.
-
It's a Starting Grants project sponsored by University of Padua and Fondazione Cassa di Risparmio di Padova e di Rovigo. The project aims to promote the development and evolution of user-oriented keyword based search systems for structured data by defining and implementing large, open, public and sustainable evaluation activities. DAKKAR is a joint project with Department of Engineering "Enzo Ferrari", University of Modena and Reggio Emilia; Department of Computer, Control, and Management Engineering "Antonio Ruberti", Sapienza University of Rome.
-
CDC is a Supporting TAlent in ReSearch@University of Padova (STARS Grants). Principal investigator: Gianmaria Silvello.
The computational problem targeted by CDC is to automatically generate complete citations for general queries over evolving data sources represented by diverse data models. The aim of this research program is to design the first well-founded model as well as to develop efficient algorithms and a solid citation system for citing data. This research program is timely because the paradigm shift towards data-intensive science is happening now and scientific communication must adapt as quickly as possible to the new ways in which science progresses; and, it is ambitious because it shapes a new field in computer science as well as it tackles with a uniform approach a range of computational issues, query languages and data models that have never been treated with a shared vision before. The broader impact of this research will be on scientists and data centers that curate, elaborate and publish data, on government agencies that direct research investments, and on research performance measures (e.g., the h-index) that will be based also on data and not only on text-based contributions.
Past International Projects
-
It aims at addressing the challenge of implementing good quality standardised file formats for preserving data content in the long term. The main objective is to give memory institutions full control of the process of the conformity tests of files to be ingested into archives and to develop modular and flexible software tools to this end.
-
It aims at launching and establishing a cooperative network of researchers, practitioners, and application domain specialists who work in fields related to semantic data management, the Semantic Web, information retrieval, artificial intelligence, machine learning and natural language processing, in order to coordinate collaboration among them and to enable research activity and technology transfer in the area of keyword-based search over structured data sources.
-
It aims at achieving an evaluation methodology directed at user-oriented interactive evaluation, a new and tested set of interactive evaluation metrics, infrastructure and test suites based on these and an ongoing collaborative forum with evaluation cycles with a focus on evaluating information access systems, as well as producing a European network of new researchers trained in the improved methodologies.
-
It aims at delivering innovative adaptive services and an interactive user environment which dynamically tailors the investigation, comprehension and enrichment of digital humanities artefacts and collections. Through the provision of such functionality, CULTURA can empower all users to investigate, comprehend and contribute to digital cultural collections.
-
It aims at providing a virtual laboratory for conducting participative research and experimentation to carry out, advance and bring automation into the evaluation and benchmarking of complex multilingual and multimedia information systems, by facilitating management and offering access, curation, preservation, re-use, analysis, visualization, and mining of the collected experimental data.
-
It develops services and components for the Europeana digital library with a special focus on multilinguality and interoperability.
-
It aims at delivering the European Digital Library as an operational service and the community behind it.
-
It fosters and promotes the experimental evaluation of multilingual information access systems.
Role: Leader of the unit of the Department; leader of WP2 about the organization of the CLEF evaluation campaigns and the design and development of the evaluation infrastructure; leader of task 2.4 about the systematic experiments which study the impact of languages over system components and are carried out in Grid@CLEF. -
It aims at improving The European Library, which is the access point to 48 national libraries across Europe, and delivers components and additional functionalities to it.
-
It delivers advanced multimedia (audio, text, images) search capabilities over P2P networks.
-
It is the European network of excellence on digital libraries. It developed the DELOS reference model for digital libraries, which provided the foundations for defining what a digital library is, and delivered the DelosDLMS, the next generation digital library management systems complying with the reference model.
Past National Projects
-
Sistema Informativo Archivistico Regionale, Regional Archival Information System (SIAR) Project.
It is a project aimed to develop a distributed Digital Library System (DLS) for describing, managing, accessing and sharing archival resources. SIAR is a joint project with the Italian Veneto Region and the "Sopraintendenza Archivistica per il Veneto" (Archival Regional Board of the Ministry of Cultural Heritage).
-
It is a project aimed at implementing the surveillance of diseases of pets of the Veneto Region. The project designs and develops a Web-based application for managing and accessing the diagnoses of transmittable and non-transmittable diseases of dogs and cats made by veterinarians in their practices, in hospitals, in kennels and catteries.
Role: Participant of the unit of the Department. -
It is a project aimed at carrying out a feasibility study for a search engine in the medical domain.
-
It is a project of the Veneto Region aimed at designing and developing the portal to the libraries of the Region, offering advanced services such as annotation or geo-spatial location.
-
It is a project of the Direzione Generale Archivi (DGA) of the Ministry of Cultural Heritage and Activities for the design and development of a national archival system.
-
It is a national CNR project to develop methods and components to deliver enhanced content to the end-users of both digital libraries and the Web.