Tommaso Agnoloni

Domain Adaptation for Dependency Parsing at Evalita 2011

The domain adaptation task was aimed at investigating techniques for adapting state–of–the–art dependency parsing systems to new domains. Both the language dealt with, i.e. Italian, and the target domain, namely the legal domain, represent two main novelties of the task organised at Evalita 2011 with respect to previous domain adaptation initiatives. In this paper, we define the task and describe how the datasets were created from different resources. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results.

Ontology Based Legislative Drafting: Design and Implementation of a Multilingual Knowledge Resource

The DALOS project aims at ensuring coherence and alignment in the legislative language, providing law-makers with knowledge management tools to improve the control over the multilingual complexity of European legislation and over the linguistic and conceptual issues involved in its transposition into national laws. This paper describes the design and implementation activities performed on the basis of a set of parallel texts in different languages on a specific legal topic. Natural language processing techniques have been applied to automatically build lexicons for each language. Lexical and conceptual multilingual alignment has been accomplished exploiting terms position in parallel documents. An ontology describing entities involved in the chosen domain has been developed in order to provide a semantic description of terms in lexicons. A modular integration of such resources, represented in RDF/OWL standard format, allowed their effective and flexible access from a legislative drafting application prototype, able to enrich legal documents with terms mark-up and semantic annotations.

Modelling semantic profiles in legislative documents for enhanced norm accessibility

In this paper an approach to the Semantic Web in the legal domain is discussed: it is obtained by modelling legislative document semantic profiles using a model of normative provisions. An implementation of this approach through RDF/OWL able to describe provisions and their relations is presented. In particular, an implementation of Hohfeldian legal fundamental relations between provisions, as well as a reasoning example by using the proposed approach is shown.

Semantic web standards and ontologies for legislative drafting support

Machine readable open public data and the issue of multilingual web are open challenges promising to transform the relationship between citizens and European institutions. In this context the DA- LOS1 project aims at ensuring coherence and alignment in the legislative language, providing law-makers with knowledge management tools to improve the control over the multilingual complexity of European legislation and over the linguistic and conceptual issues involved in its transposition into national laws. This paper describes the design and implementation activities performed on the basis of a set of parallel texts in different languages on a specific legal topic. Natural language processing techniques have been applied to automatically build lexicons for each language. Lexical and conceptual multilingual alignment has been accomplished exploiting terms position in parallel documents. An ontology describing entities involved in the chosen domain has been developed in order to provide a semantic description of terms in lexicons. A modular integration of such resources, represented in RDF/OWL standard format, allowed their effective and flexible access from a legislative drafting application prototype, able to enrich legal documents with terms mark-up and semantic annotations.

A Survey on Legal Research Monograph Evaluation in Italy

The chapter presents an original survey carried out in 2015 on legal research monographs evaluation. The target respondents were the Italian legal community. The rate of answers was quite high (taking into account a low level of national responses to mail or web surveys), reaching 26% of all professors and researchers. The survey examines in detail the criteria of research quality adopted by legal scholars. It also delivers a number of recommendations with respect to peer review, journal classification, and other evaluation practice.

Towards ECLI 2.0

The European Case Law Identifier (ECLI) was established in 2010. It has been implemented by three European courts and (partly or in full) by twelve Member States, while eight Member States are preparing an implementation. During these implementations various issues concerning the format, metadata and the architecture of ECLI have surfaced, while in the meantime technological insights have progressed. To improve the accessibility of current and future case law repositories an ECLI 2.0 needs to be considered. Given the implementations realized, backwards compatibility is an absolute prerequisite. In this paper the various issues and possible solutions are discussed.