Projects

I’m part of the Social Computing group at the Dept. of Computer Science.
I’m part of the Big Data Lab “Despina” at the Dept. of Economics.

FACILEX (as partner leader)

FACILEX aims at providing a multilevel online platform grounded on a comprehensive comparative legal analysis, focusing on the implementation of EU mutual recognition instruments in different Member States by means of AI tools and language technologies.
Tags: #Legal-Informatics, #Natural-Language-Processing #Decision-Support-Systems

ADELE (as partner leader)

ADELE aims at applying legal analytics (LA) – a blend of data science, machine learning and natural language processing techniques – to judicial decisions, extracting knowledge and engaging in outcome predictions, building a pilot tool to support legal research and decision-making processes in the judiciary.
Tags: #Legal-Informatics, #Natural-Language-Processing #Machine Learning

Cross-Justice (as partner leader)

Cross-Justice aims at creating an online platform to access knowledge and legal advice on procedural rights, thus providing a free service, mainly directed to legal professionals, but accessible to all EU citizens and organisations.
Tags: #Legal-Informatics, #Natural-Language-Processing #Decision-Support-Systems

InterLex (as Coordinator) [ended]

InterLex aims at developing a platform to provide information, decision support and training on private international law. It addresses the identification of the legal system having jurisdiction and of the national law to be applied to a case, as well as the retrieval of relevant legal materials.
Tags: #Knowledge-Representation, #Legal-Informatics, #Natural-Language-Processing #Decision-Support-Systems

Semagram (as Principal Investigator) [ended]

A semagram is a flexible structure for encoding the semantics of a givenconcept via a slot-filler structure. This “semagram base” is the result of a systematic analysis, unification and extension of semantic relations (or slots) derived from different resources: ANW dictionary, Visual Attributes and Property Norms.
Tags: #Computational-Linguistics, #Lexical-Semantics
Resource link ; paper link

SemBurst (as Principal Investigator) [ended]

The aim of this project is to apply distributional semantics methods not only to words, but to sets of semantic information taken from existing semantic resources and associated with words in syntactic contexts. The idea is to inject semantics into vector space models to find correlations between statements (rather than between words).
Tags: #Computational-Linguistics, #Distributional-Semantics, #Semantic-Vector-Spaces, #Semantic-Norms, #Similarity-Reasoning

BO-ECLI (as partner leader) [ended]

This project aims at improve accessibility of case law by automatically extracting legal references expressed by the judge by way of textual citations using Information Extraction and Natural Language Processing technologies.
Tags: #Legal-Informatics, #Named-Entity-Linking

MIREL (as work-package leader) [ended]

The MIREL project has the goal of creating an international and inter-sectorial network to define a formal framework and to develop tools for MIning and REasoning with Legal texts, with the aim of translating these legal texts into formal representations that can be used for querying norms, compliance checking, and decision support.

Tags: #Legal-Informatics, #Data-Mining, #Computational-Linguistics, #Knowledge-Representation, #Ontology-Learning

GENOME (as scientific coordinator) [ended]
The aim of this research project is to map the evolution of knowledge in the History of Economic Thought by representing the creation and the dynamics of new concepts and ideas as appeared in academic publishing.
Tags: #Data-Mining, #Topic-Extraction, #Topic-Evolution, #Economics

EUCases (as classification task-leader) [ended]

EUCases was a collaborative Research Project supported by Seventh Framework Programme (FP7) funding. The project developed a unique pan-European law and case law Linking Platform transforming multilingual legal open data into linked open data after semantic and structural analysis.
Tags: #Legal-Informatics, #Text-Classification, #Text-Summarization

EasyTown (as Principal Investigator) [ended]
EasyTown is one of the projects that have been awarded with a national grant on the topic Cities and Communities and Social Innovation. It provides new technologies for a more simple and direct access by citizens to the normative and local dimension.
Tags: #Legal-Informatics, Text-Summarization, #Information-Retrival, #Smart-Cities

KnowYouAll (as Principal Investigator) [ended]

KnowYouAll is a project for semantic search in personal textual data that relies on a Named Entity Recognition module and an interactive query system. It won a national competition called Working Capital, organized by Telecom Italia in 2012.
Tags: #Computational-Linguistics, #Named-Entity-Recognition, #Text-Visualization

EU Legal Culture (as scientific collaborator) [ended]

The project addresses the question “How a new European legal culture is being shaped in Europe?” to make lawyers and citizens more aware of the dynamics of European law and how they impact on their work and on their life.
Tags: #Legal-Informatics, #Legal-Ontologies

ICT4LAW (as scientific collaborator) [ended]

ICT4LAW is a large interdisciplinary research project involving several university departments and industry partners. The goal is to create novel services for citizens, enterprises, public administration and policy makers. My role includes legal data analysis for classification of laws and ontologies construction.
Tags: #Computational-Linguistics, #Text-Classification, #Legal-Informatics, #Legal-Ontologies

ATLAS (as scientific collaborator) [ended]

The ATLAS project targets automatic translation from Italian to Italian Sign Language (LIS) of deaf people. The aim of the project is to create applications to improve inclusion of deaf people by providing contents in their language using virtual characters.
Tags: #Computational-Linguistics, #Subcategorization-frames, #Semantic-Role-Labeling

DynamicTV (as scientific collaborator) [ended]
The project consisted of a system to classify and recommend TV contents based on domain ontologies and texts. Large text corpora, like newspapers archives, used to contain dynamic data from both a cultural and a linguistics point of view. Domain ontologies, on the other hand, represent a static and domain-specific knowledge. The project aimed at bridging the gap between these different sources of information for improving content classification and recommendation.
Tags: #Data-Mining, Text-Classification, Content-Recommendation, Domain-Ontologies, TV-contents