Lynx: A knowledge-based AI service platform for content processing, enrichment and analysis for the legal domain

Schneider, Julián Moreno; Rehm, Georg; Montiel-Ponsoda, Elena; Rodrı́guez-Doncel, Victor; Martín-Chozas, Patricia; Navas-Loro, María; Kaltenböck, Martin; Revenko, Artem; Karampatakis, Sotirios; Sageder, Christian; Gracia, Jorge; Maganza, Filippo; Kernerman, Ilan; Lonke, Dorielle; Lagzdiņš, Andis; Bosque-Gil, Julia; Verhoeven, Pieter; Diaz, Elsa Gomez; Ballesteros, Pascual Boil

doi:10.1016/j.is.2021.101966

Cited by 13 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another virtual assistant, Lynx, utilizes knowledge graphs technologies to manage an extensive collection of law documents from Europe [5]. Their project began with a focus on addressing the multilingual nature of the laws by employing KG technologies [14].…”

Section: Knowledge Graph For Virtual Assistantsmentioning

confidence: 99%

“…In this project, a linked data structure was built using Wikipedia hyperlink data. In the legal domain, the Lynx project utilized a combination of information retrieval and knowledge graphs to develop their virtual assistant for legal use [5]. However, our system is dissimilar from Lynx in that our data comprises Indonesian language while theirs utilizes multilingual data.…”

Section: Legal Virtual Assistant Requirementsmentioning

confidence: 99%

“…In the legal domain, the application of knowledge graphs is evident in initiatives such as EUR-Lex 5 and project Lynx [5]. 6 The latter aims to standardize legal documents in Europe by incorporating the European Legislation Identifier (ELI).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Virtual Assistant for Legal Domain Based on Information Retrieval and Knowledge Graphs

Faisal,

Darari,

Ghifari

et al. 2023

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

Virtual assistants have gained popularity across various domains, including the legal field, where they serve to offer guidance and aid in the form of law retrieval. In this research, our aim is to develop a legal virtual assistant that combines knowledge graphs (KGs) and information retrieval (IR) techniques. This hybrid approach allows us to provide accurate answers extracted from structured interconnected data while simultaneously cater to a diverse range of legal inquiries. We categorize these inquiries into a few distinct use cases: definition lookup, law component lookup, sanctions, and domain knowledge. Our system encompasses a chatbot platform, knowledge graph querying, and information retrieval. Specifically, we construct a VA system over a legal knowledge graph pertaining to the Indonesian Act concerning Manpower or Labor (UU Ketenagakerjaan) and the Indonesian Act concerning the Creation of Jobs (UU Cipta Kerja). This marks the creation of the first legal virtual assistant in the Indonesian context that combines KG and IR methodologies. To evaluate the effectiveness of our prototype system, we conduct tests using a variety of labor law-related questions, ranging in difficulty. The integration of knowledge graphs and information retrieval proves to significantly improve the support provided for a wide range of potential applications in the legal field.

show abstract

Section: Knowledge Graph For Virtual Assistantsmentioning

confidence: 99%

Section: Legal Virtual Assistant Requirementsmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Virtual Assistant for Legal Domain Based on Information Retrieval and Knowledge Graphs

Faisal,

Darari,

Ghifari

et al. 2023

Jurnal Ilmu Komputer dan Informasi

View full text Add to dashboard Cite

show abstract

“…From a legal viewpoint, fundamental questions and principles related to obligations/responsibilities, and liability/rights/accountability remain valid [63]. IoT ecosystems on the WoD involve different types of contracts, licenses, insurances, patents, privacy, and consumer and data protection (see, for the European framework [10], on NLP for legal services, [64]). However, the traditional legal approach will not be enough as the Fewer than 10% of drinkers, for example, account for over half the hard liquor sold.…”

Section: Socio-legal Ecosystemsmentioning

confidence: 99%

Law, Socio-Legal Governance, the Internet of Things, and Industry 4.0: A Middle-Out/Inside-Out Approach

Casanovas

Koker

Hashmi

2022

View full text Add to dashboard Cite

The Web of Data, the Internet of Things, and Industry 4.0 are converging, and society is challenged to ensure that appropriate regulatory responses can uphold the rule of law fairly and effectively in this emerging context. The challenge extends beyond merely submitting digital processes to the law. We contend that the 20th century notion of ‘legal order’ alone will not be suitable to produce the social order that the law should bring. The article explores the concepts of rule of law and of legal governance in digital and blockchain environments. We position legal governance from an empirical perspective, i.e., as an explanatory and validation concept to support the implementation of the rule of law in the new digital environments. As a novel contribution, this article (i) progresses some of the work done on the metarule of law and complements the SMART middle-out approach with an inside-out approach to digital regulatory systems and legal compliance models; (ii) sets the state-of-the-art and identifies the way to explain and validate legal information flows and hybrid agents’ behaviour; (iii) describes a phenomenological and historical approach to legal and political forms; and (iv) shows the utility of separating enabling and driving regulatory systems.

show abstract

“…ChatGPT extracted from Polanyi's idea of "embedding -deembedding" interaction of ChatGPT theoretical framework, which provides an important perspective for us to analyze the relationship between ChatGPT and society.ChatGPT operation "de-embedding" may cause algorithmic problems in society. The operation of ChatGPT "de-embedding" may cause harm to society, such as algorithmic logic risk, data security risk, and general socialization risk [10][11][12]. In this regard, the state should assume the responsibility of sheltering the society and preventing it by strengthening the national regulatory capacity, promoting enterprises to actively fulfill their obligations, and facilitating the social multi-dimensional co-management so as to make ChatGPT "embedded" in the society and maintain it on the track of "technology for good" [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Improvement Path of Legal System Related to ChatGPT Application Combined with Decision Tree Algorithm

Guo,

Wang

2024

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

Artificial Intelligence (AI) has been widely used in the social and legal fields, and ChatGPT, after AI painting, has once again set off a wave of discussion on whether AI and its generated works can obtain legal protection. Starting from the theoretical orientation of the origin of ChatGPT legal governance, this paper proposes the legal positioning and layered governance framework of ChatGPT application. It explores the role mechanism of ChatGPT empowering legal modernization and combs through the realistic dilemmas of ChatGPT-generated content data compliance legalization. To effectively analyze legal risks in the process of the ChatGPT application, data crawling technology and SMOTE oversampling technology are utilized to obtain ChatGPT application data and produce datasets. The Stacking integration strategy is introduced to combine the Random Forest in the Decision Tree Algorithm, GBDT algorithm, and Support Vector Machine to construct the legal risk prediction model of the ChatGPT application. For the effectiveness of the model, the ChatGPT application dataset is used to analyze the accuracy, ROC curve, and AUC value, which provides a reference for improving the legal system related to the ChatGPT application. The results show that the accuracy of the SVM classifier reaches 0.839, the correctness of the GBDT model is 0.947, and the AUC value of ChatGPT legal risk prediction based on the Stacking integration strategy is 0.947. Based on the inspiration of the decision tree algorithm, the improvement of the legal system related to the ChatGPT application should be improved in terms of generating content and allocating risk. Based on the insights of the decision tree algorithm, the improvement of the legal system related to the ChatGPT application should be made based on the dimensions of generation content and risk allocation.

show abstract

Lynx: A knowledge-based AI service platform for content processing, enrichment and analysis for the legal domain

Cited by 13 publications

References 7 publications

A Hybrid Virtual Assistant for Legal Domain Based on Information Retrieval and Knowledge Graphs

A Hybrid Virtual Assistant for Legal Domain Based on Information Retrieval and Knowledge Graphs

Law, Socio-Legal Governance, the Internet of Things, and Industry 4.0: A Middle-Out/Inside-Out Approach

Improvement Path of Legal System Related to ChatGPT Application Combined with Decision Tree Algorithm

Contact Info

Product

Resources

About