ProLeMAS · PROcessing LEgal language in normative Multi-Agent Systems
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2015-06-01 → 2017-05-31
- EU contribution
- €160,800
- Participants
- 1
- Scheme
- MSCA-IF-EF-ST
Lines connect the coordinator with its partners.
Results in brief
ProLeMAS: PROcessing LEgal language in normative Multi-Agent Systems
ProLeMAS aimed at devising a new logic for normative reasoning in multi-agent systems and implementing a pipeline from legal text to these formulae. Current technologies in legal informatics, both at the academic and the industrial level, restrict their scope and capabilities to the terminological/syntactic level. Examples are the Eunomos [Boella et al., 2016] or the Eurocases system (eurocases.eu), distributed by APIS (http://www.apis.bg/en/), the Bulgarian company that hosted the secondment of ProLeMAS. Although these techniques provide valid solutions to help navigate legislation and retrieve information, their overall usefulness and effectiveness are limited due to their focus on terminological issues while disregarding the specific semantic aspects of law. This was the main issue/objective addressed in ProLeMAS, which was fully achieved by the design of a new logic, called reified Input/Ouput logic, whose definition has been published in the Journal of Logic and Computation [Robaldo and Sun, 2017]. Reified Input/Output logic is currently proposed in several ongoing/future projects as the underlying formalism to represent norms in natural language. The most important is DAPRECO (https://www.fnr.lu/projects/data-protection-regulation-compliance-2), which has been retained for funding by the Luxembourg National Research Fund in October 2016. On the other hand, although experiments on several novel NLP procedures and techniques has been carried out (results have been published in several conference papers) to process legal texts and reason on them, automatic conversion from legal text to reified Input/Output logic was deemed to be too hard. In light of this, the tool that will be developed in DAPRECO will interface NPL procedures to allow for the SEMI-AUTOMATIC constructions of the formulae. More details are provided in the two sections below.
Data: CORDIS, © European Union
Project objective
Existing technologies usually represent norms as formal rules involving deontic operators. Such a rule-based representation of norms is not suitable to handle real data. Norms emerge from laws via an interpretation process. The methodology of Normative Multi-agent Systems (NorMas) by prof. Boella and prof. van der Torre has been conceived to overcome these limits. Nevertheless, the current formalization of NorMas features two main limitations. Firstly, its models are based on deontic logic such as input/output logic. Deontic logic is typically propositional, i.e. its basic components are propositions connected by modal operators. A proposition basically refers to a whole sentence. On the other hand, natural language semantics includes a wide range of fine-grained intra-sentence linguistic phenomena: named entities, scope-sensitive operators, etc. It is then necessary to move beyond the propositional level, i.e. to enhance the expressivity of NorMas fit to formalize the meaning of the phrases constituting the sentences (noun phrases, verbal phrases, named entities, etc.). Secondly, NorMas has never been implemented and tested on real legal text. Currently, NorMas is only a promising logical theory, but it is time to see how it behaves on real data, in order to make it suitable for commercial applications. Drawing from my past experience in natural language semantics, parsing, and corpora building, I propose a project for extending NorMas in that sense, leading to ProLeMAS: (Processing Legal language in normative Multi-Agent Systems), a new logic for normative reasoning in multi-agent systems. In particular, the present project aims at (1) filling the gap between the current formalization of NorMas and the richness of natural language semantics (2) Implementing a pipeline from legal text to ProLeMAS formulae, passing through parsing and reasoning.
Original text from CORDIS.
Participants
- UNIVERSITE DU LUXEMBOURG · ESCH-SUR-ALZETTECoordinatorLuxembourg
Links
Data: CORDIS, © European Union