Integrating Domain Knowledge in AI-Assisted Criminal Sentencing of Drug Trafficking Cases

Tien Hsuan Wu, Ben Kao, Anne S.Y. Cheung, Michael M.K. Cheung, Chen Wang, Yongxi Chen, Guowen Yuan, Reynold Cheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

Abstract

Judgment prediction is the task of predicting various outcomes of legal cases of which sentencing prediction is one of the most important yet difficult challenges. We study the applicability of machine learning (ML) techniques in predicting prison terms of drug trafficking cases. In particular, we study how legal domain knowledge can be integrated with ML models to construct highly accurate predictors. We illustrate how our criminal sentence predictors can be applied to address four important issues in legal knowledge management, which include (1) discovery of model drifts in legal rules, (2) identification of critical features in legal judgments, (3) fairness in machine predictions, and (4) explainability of machine predictions.

Original languageEnglish
Title of host publicationLegal Knowledge and Information Systems
Subtitle of host publicationJURIX 2020 - 33rd Annual Conference, Brno, Czech Republic, December 9–11, 2020
EditorsSerena Villata, Jakub Harašta, Petr Křemen
Place of PublicationAmsterdam
PublisherIOS Press BV
Pages174-183
Number of pages10
ISBN (Electronic)978-1-64368-151-1
ISBN (Print)978-1-64368-150-4
DOIs
Publication statusPublished - Dec 2020
Externally publishedYes
Event33rd International Conference on Legal Knowledge and Information Systems, JURIX 2020 - Brno, Czech Republic
Duration: 9 Dec 202011 Dec 2020
https://ebooks.iospress.nl/volume/legal-knowledge-and-information-systems-jurix-2020-the-thirty-third-annual-conference-brno-czech-republic-december-911-2020

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS Press
Volume334
ISSN (Print)0922-6389
ISSN (Electronic)1879-8314

Conference

Conference33rd International Conference on Legal Knowledge and Information Systems, JURIX 2020
Abbreviated titleJURIX 2020
Country/TerritoryCzech Republic
CityBrno
Period9/12/2011/12/20
OtherThe field of legal knowledge and information systems has traditionally been concerned with the subjects of legal knowledge representation and engineering, computational models of legal reasoning, and the analysis of legal data, but recent years have also seen an increasing interest in the application of machine learning methods to ease and empower the everyday activities of legal experts.

This book presents the proceedings of the 33rd International Conference on Legal Knowledge and Information Systems (JURIX 2020), organised this year as a virtual event on 9–11 December 2020 due to restrictions resulting from the Covid-19 pandemic. For more than three decades, the annual JURIX international conference, which now also includes demo papers, has provided a platform for academics and practitioners to exchange knowledge about theoretical research and applications in concrete legal use cases. A total of 85 submissions by 255 authors from 28 countries were received for the conference, and after a rigorous review process, 20 were selected for publication as full papers, 14 as short papers, and 5 as demo papers. This selection process resulted in a total acceptance rate of 40% (full and short papers) and a competitive 23.5% acceptance rate for full papers. Topics span from computational models of legal argumentation, case-based reasoning, legal ontologies, smart contracts, privacy management and evidential reasoning to information extraction from different types of text in legal documents, and ethical dilemmas.

Providing a state-of-the-art overview of developments in the field, this book will be of interest to all those working with legal knowledge and information systems.
Internet address

Fingerprint

Dive into the research topics of 'Integrating Domain Knowledge in AI-Assisted Criminal Sentencing of Drug Trafficking Cases'. Together they form a unique fingerprint.

Cite this