Values Embedded in Legal Artificial Intelligence

Surden, Harry

doi:10.1109/mts.2022.3147542

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, deep learning models are often considered as black boxes which are difficult to understand and to interpret. This is a major concern as basic legal principles require that legal decision makers must be able to explain how they came to the decisions (Surden, 2022). Another concern is the accountability and responsibility attribution to human agents involved in the development, deployment and usage of AI‐based decision making.…”

Section: Discussionmentioning

confidence: 99%

“…Artificial intelligence, as the engine of digitalisation, has a central role in improving the experience of providers and users of justice systems. The efficiency‐increasing capacity of artificial intelligence has been recognized through the increased incorporation of AI‐based systems in the application and the administration of law (Surden, 2022). Natural Language Processing (NLP), as a subfield of artificial intelligence, has been used in several legal technologies such as automatic summarization (Gelbart & Smith, 1991; Polsley et al, 2016) and classification (de Araujo et al, 2020; Li et al, 2019) of legal documents, identification and specification of normative provisions' categories (Berrazega et al, 2016; Bouhyaoui et al, 2018), legal question answering systems (Do et al, 2017; Morimoto et al, 2017; Taniguchi et al, 2018), documents automation (Hassan & Le, 2020) and court decisions analysis (Metsker et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of court decision from Arabic documents using deep learning

Zahir

2023

Expert Systems

View full text Add to dashboard Cite

The increasing amount of electronic legal documents represents a great opportunity for the development of intelligent computational systems for legal texts processing and classification. Most of these systems use classical machine learning and large datasets in English. This paper proposes an approach to automatically predict legal case outcome from written description of the events in Arabic using deep learning.An in-house corpus from the decisions of the Moroccan Court of Cassation is built and used to train a deep learning model that predicts judgement. As the created corpus is of limited size, a new data augmentation method is proposed to boost the prediction performance. Two settings for text representation are tested, namely FastText and GloVe embeddings, and multiple deep learning models architectures are tested. The proposed approach succeeds in predicting judicial decisions of the Moroccan Court of Cassation with an accuracy of 80.51% on six classes. Even with a small dataset, the proposed data augmentation method was helpful in improving the overall models' performance. Despite the advancement in the area of legal judgement prediction over the years, this work is the first attempt to predict legal outcome using the documents of the Moroccan Cassation court. The corpus created in the context of this work will be made publicly available to the community.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of court decision from Arabic documents using deep learning

Zahir

2023

Expert Systems

View full text Add to dashboard Cite

show abstract

Big data and AI-driven evidence analysis: a global perspective on citation trends, accessibility, and future research in legal applications

Kerdvibulvech

2024

J Big Data

View full text Add to dashboard Cite

RETRACTED: Algorithmic Bias: An Integrative Review and Scope for Future Research

CHAUDHARY

2024

Preprint

View full text Add to dashboard Cite

Today Artificial Intelligence and Machine Learning (ML) algorithms are influencing various aspects of human life, for instance - healthcare, loan provision, education, recruitment, and so on. But these systems are facing the issue of algorithmic bias, they can potentially generate socially biased outcomes, and they can enhance inequalities in the workplace as well as in society, even when there is no intention of doing so. The current literature on algorithmic bias is progressing in various directions in the absence of a robust theoretical foundation. Therefore, there is a requirement for a consolidation to provide a comprehensive and up-to-date summary of research in the area. This study presents an integrative review of the current body of literature on algorithmic bias, considering the diverse domains, samples, and methodologies employed in previous studies. This analysis highlights multiple gaps in the algorithmic bias domain. These gaps comprise definitional issues, insufficient theoretical foundations, thematic tensions, and inconsistencies in current literature. A potential future research avenue is proposed, which consists of a collection of various themes and research gaps. Also, a theoretical framework is provided that might serve as a guiding principle for future research in the domain of algorithmic bias.

show abstract

Values Embedded in Legal Artificial Intelligence

Cited by 4 publications

References 14 publications

Prediction of court decision from Arabic documents using deep learning

Prediction of court decision from Arabic documents using deep learning

Big data and AI-driven evidence analysis: a global perspective on citation trends, accessibility, and future research in legal applications

RETRACTED: Algorithmic Bias: An Integrative Review and Scope for Future Research

Contact Info

Product

Resources

About