Reuse and Reengineering of Non-ontological Resources in the Legal Domain

Author(s):  
Cristiana Santos ◽  
Pompeu Casanovas ◽  
Víctor Rodríguez-Doncel ◽  
Leendert van der Torre
Keyword(s):  
2020 ◽  
Vol 7 (3) ◽  
pp. 471-494
Author(s):  
Katsumi NITTA ◽  
Ken SATOH

AbstractArtificial intelligence (AI) and law is an AI research area that has a history spanning more than 50 years. In the early stages, several legal-expert systems were developed. Legal-expert systems are tools designed to realize fair judgments in court. In addition to this research, as information and communication technologies and AI technologies have progressed, AI and law has broadened its view from legal-expert systems to legal analytics and, recently, a lot of machine-learning and text-processing techniques have been employed to analyze legal information. The research trends are the same in Japan as well and not only people involved with legal-expert systems, but also those involved with natural language processing as well as lawyers have become interested in AI and law. This report introduces the history of and the research activities on applying AI to the legal domain in Japan.


2021 ◽  
pp. 1-13
Author(s):  
Jenish Dhanani ◽  
Rupa Mehta ◽  
Dipti Rana

Legal practitioners analyze relevant previous judgments to prepare favorable and advantageous arguments for an ongoing case. In Legal domain, recommender systems (RS) effectively identify and recommend referentially and/or semantically relevant judgments. Due to the availability of enormous amounts of judgments, RS needs to compute pairwise similarity scores for all unique judgment pairs in advance, aiming to minimize the recommendation response time. This practice introduces the scalability issue as the number of pairs to be computed increases quadratically with the number of judgments i.e., O (n2). However, there is a limited number of pairs consisting of strong relevance among the judgments. Therefore, it is insignificant to compute similarities for pairs consisting of trivial relevance between judgments. To address the scalability issue, this research proposes a graph clustering based novel Legal Document Recommendation System (LDRS) that forms clusters of referentially similar judgments and within those clusters find semantically relevant judgments. Hence, pairwise similarity scores are computed for each cluster to restrict search space within-cluster only instead of the entire corpus. Thus, the proposed LDRS severely reduces the number of similarity computations that enable large numbers of judgments to be handled. It exploits a highly scalable Louvain approach to cluster judgment citation network, and Doc2Vec to capture the semantic relevance among judgments within a cluster. The efficacy and efficiency of the proposed LDRS are evaluated and analyzed using the large real-life judgments of the Supreme Court of India. The experimental results demonstrate the encouraging performance of proposed LDRS in terms of Accuracy, F1-Scores, MCC Scores, and computational complexity, which validates the applicability for scalable recommender systems.


Author(s):  
Alain Klarsfeld ◽  
Gaëlle Cachat-Rosset

Equality is a concept open to many interpretations in the legal domain, with equality as equal treatment dominating the scene in the bureaucratic nation-state. But there are many possibilities offered by legal instruments to go beyond strict equality of treatment, in order to ensure equality of opportunity (a somehow nebulous concept) and equality of outcomes. Legislation can be sorted along a continuum, from the most discriminatory ones (“negative discrimination laws”) such as laws that prescribe prison sentences for people accused of being in same-sex relationships, to the most protective ones, labeled as “mandated outcome laws” (i.e., laws that prescribe quotas for designated groups) through “legal vacuum” (when laws neither discriminate nor protect), “restricted equal treatment” (when data collection by employers to monitor progress is forbidden or restricted), “equal treatment” (treating everyone the same with no consideration for outcomes), “encouraged progress” (when data collection to monitor progress on specific outcomes is mandatory for employers), and mandated progress (when goals have to be fixed and reached within a defined time frame on specified outcomes). Specific countries’ national legislation testify that some countries moved gradually along the continuum by introducing laws of increasing mandate, while (a few) others introduced outcome mandates directly and early on, as part of their core legal foundations. The public sector tends to be more protective than the private sector. A major hurdle in most countries is the enforcement of equality laws, mostly relying on individuals initiating litigation.


2020 ◽  
pp. 70-73
Author(s):  
Mehran Kamkarhaghighi ◽  
Afsaneh Towhidi ◽  
Masoud Makrehchi

Semantic Web ◽  
2016 ◽  
Vol 7 (3) ◽  
pp. 213-227 ◽  
Author(s):  
Pompeu Casanovas ◽  
Monica Palmirani ◽  
Silvio Peroni ◽  
Tom van Engers ◽  
Fabio Vitali
Keyword(s):  

2008 ◽  
Vol 20 (6) ◽  
pp. 1043-1064 ◽  
Author(s):  
Fleurie Nievelstein ◽  
Tamara van Gog ◽  
Henny P. A. Boshuizen ◽  
Frans J. Prins
Keyword(s):  

2021 ◽  
Author(s):  
Mirna El Ghosh ◽  
Habib Abdulrab

The primary goal of the General Data Protection Regulation (GDPR) is to regulate the rights and duties of citizens and organizations over personal data protection. Implementing the GDPR is recently gaining much importance for legal reasoning and compliance checking purposes. In this work, we aim to capture the basics of GDPR in a well-founded legal domain modular ontology named OPPD (Ontology for the Protection of Personal Data). Ontology-Driven Conceptual Modeling (ODCM), ontology layering, modularization, and reuse processes are applied. These processes aim to support the ontology engineer in overcoming the complexity of the legal knowledge and developing an ontology model faithful to reality. ODCM is used for grounding OPPD in the Unified Foundational Ontology (UFO). Ontology modularization and layering aim to simplify the ontology building process. Ontology reuse focuses on selecting and reusing Conceptual Ontology Patterns (COPs) from UFO and the legal core ontology UFO-L. OPPD intends to overcome the lack of a representation of legal procedures that most ontologies encountered. The potential use of OPPD is proposed to formalize the GDPR rules by combining ontological reasoning and Logic Programming.


2013 ◽  
Vol 11 (3) ◽  
pp. 237-251
Author(s):  
Erin Kruger

This paper takes the ‘visual’ as the primary subject to engage in a dialogue about surveillance by drawing upon the specific case of the genetic image. Specifically, the genetic image has shifted from the ‘one gene for one identification’ model used in the criminal law to, what are now, categorical, contextual and pattern-based configurations of DNA profiling that are able to compare multiple genetic samples in a singular image. The ability to profile genetics for law and security purposes is, thus, protracting well beyond the confines of the criminal legal domain (i.e. the crime scene, forensic laboratory, courtroom) and into the realm of surveillance: national security, defense, immigration, military and even humanitarian domains. Such a notable transition in visual profiling has also been met with a synonymous reformation in the status of genetic data as it converts from evidence in the realm of criminal law to, now, intelligence in the surveillance-based contexts noted above. This visual reclassification of genetic data reorients DNA to an informing, as opposed to an identifying role. Finally, how experts, scientists, legalists and other relevant practitioners conceive and represent ‘truth’ and ‘trust’ in light of an increasingly diverse range of genetic imagery is subject for discussion.


Sign in / Sign up

Export Citation Format

Share Document