Assessing AI-Driven Translation of Arabic Legal Texts: Developing a Quality Evaluation Framework through Comparative Human–Machine Analysis

The research aims to develop a comprehensive quality assessment framework for evaluating AI-assisted translation of Arabic into English in the domain of law through a comparative human-machine analysis. Building on legal translation theory, corpus-based approaches, and Multidimensional Quality Metrics (MQM), the research identifies six dimensions of assessment: legal conceptual equivalence, terminological correctness and consistency, semantic correctness, functional and pragmatic adequacy, linguistic quality, and jurisdictional and cultural adequacy. In terms of methodology, the research uses qualitative comparison of representative legal texts in Arabic and their potential problematic machine-generated translations and contextually sensitive human-made alternatives. Seven types of translation problems have been analyzed: conceptual inaccuracy, terminological inconsistency, omission/addition, legal modality, culturally-specific terms, conditional provisions, and legal register. The findings of the study show that acceptable linguistically translations can distort legal rights, obligations, and institutions. This research argues that linguistic evaluation alone cannot be used to evaluate the quality of legal translation and suggests the integration of an error taxonomy based on severity and expert legal judgment. Future research directions include empirical research using actual machine-generated translations, larger multilingual legal corpora, expert evaluations, and interrater reliability tests.

Authors

Publication Details

Journal
International Journal of Translation and Interpretation Studies
Published
2026-11-14
DOI
https://doi.org/10.32996/ijtis.2026.6.6.4
Primary Topic
Translation Studies and Practices
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Assessing AI-Driven Translation of Arabic Legal Texts: Developing a Quality Evaluation Framework through Comparative Human–Machine Analysis

Islam Husienat, Zakaryia Almahasees, Hussein Al-Bo'ul
International Journal of Translation and Interpretation Studies
Translation Studies and Practices
article

Assessing AI-Driven Translation of Arabic Legal Texts: Developing a Quality Evaluation Framework through Comparative Human–Machine Analysis

Islam Husienat, Zakaryia Almahasees, Hussein Al-Bo'ul
article en

Abstract

The research aims to develop a comprehensive quality assessment framework for evaluating AI-assisted translation of Arabic into English in the domain of law through a comparative human-machine analysis. Building on legal translation theory, corpus-based approaches, and Multidimensional Quality Metrics (MQM), the research identifies six dimensions of assessment: legal conceptual equivalence, terminological correctness and consistency, semantic correctness, functional and pragmatic adequacy, linguistic quality, and jurisdictional and cultural adequacy. In terms of methodology, the research uses qualitative comparison of representative legal texts in Arabic and their potential problematic machine-generated translations and contextually sensitive human-made alternatives. Seven types of translation problems have been analyzed: conceptual inaccuracy, terminological inconsistency, omission/addition, legal modality, culturally-specific terms, conditional provisions, and legal register. The findings of the study show that acceptable linguistically translations can distort legal rights, obligations, and institutions. This research argues that linguistic evaluation alone cannot be used to evaluate the quality of legal translation and suggests the integration of an error taxonomy based on severity and expert legal judgment. Future research directions include empirical research using actual machine-generated translations, larger multilingual legal corpora, expert evaluations, and interrater reliability tests.

International Journal of Translation and Interpretation StudiesVol. 6(6)
Translation Studies and Practices
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon