https://www.um.edu.mt/library/oar/handle/123456789/1037 2026-08-26T15:47:20Z 2026-08-26T15:47:20Z Giampieri, Patrizia https://www.um.edu.mt/library/oar/handle/123456789/148657 2026-08-25T08:59:14Z 2023-01-01T00:00:00Z

Title: Is machine translation reliable in the legal field? A corpus-based critical comparative analysis for teaching ESP at tertiary level Authors: Giampieri, Patrizia Abstract: This paper is aimed at exploring whether and how machine translation (MT) can be relied on in the legal field. To this aim, clauses excerpted from a distribution agreement are translated from Italian into English by using the Deepl machine translation platform. In order to assess the reliability and quality of the translation, a corpus of distribution agreements written in English as a first language and as a lingua franca is composed. The contracts are sourced from the Onecle.com platform, and the reference corpus is built semi-automatically by using the BootCaT software solution. In order to retrieve documents drafted in international English and hence validated by international lawyers or businesspeople, advanced search techniques are applied. The corpus is then consulted by using the AntConc offline concordancer, and the MT is compared with corpus evidence. The paper findings highlight shortcomings in the MT related to legal formulae. Word order is sometimes incorrect and the system specificity of the legal language in the target text remains unaddressed. The paper calls for future improvements in MT software, and reports the need for translators and translation students to be acquainted with legal language style and writing conventions.

2023-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148579 2026-08-20T09:58:29Z 2024-01-01T00:00:00Z

Title: Translation product evaluation in translator training : a comparison between L1 (English > Dutch) and L2 (Dutch > English) student translations using the PIE method (preselected items evaluation) and the ATA (American translators association) framework for standardized error marking Abstract: Translation evaluation is a contentious area of study, particularly due to the degree of subjectivity of many evaluation methods, yet it is essential in translator training. Likewise, directionality is a controversial field due to the hegemony of translation into the first language (L1 translation). Nevertheless, translation into the foreign language (L2 translation) is included in most, if not all, translator training programmes in many countries.; The present study combines these two much debated fields of study into an empirical experiment conducted in translator training in Flanders. Its aim is twofold. Firstly, it provides insight into the differences between L1 and L2 translation in terms of scores and error types on the basis of the data for this study and a prior pilot study. It also compares the perceived difficulty of both translation directions with the scores achieved. From a process-oriented perspective, this study compares the time spent on the translations with the final scores. The second aim of the study is to scrutinise the evaluation process and empirically test a combined analytical evaluation method consisting of an enhanced version of PIE (Preselected Items Evaluation), an item-based analytical evaluation method, and the ATA (American Translators Association) Framework for Standardized Error Marking.; The findings reveal that, while the scores in both translation directions are low and comparable, surprisingly, the students made slightly more errors in L1 translation, despite perceiving the L2 translation as more difficult. In both translation directions, the main errors identified are terminology errors. In addition, both L1 and L2 translation are characterised by source language interference. It was not possible to establish a conclusive relation between the time spent on the translations and the final scores. As for the evaluation process, the present study reveals several limitations of PIE and the combined PIE and ATA method, and calls for further research into the application of these evaluation methods, particularly into the intersubjective consensus.; It is hoped that this study will inspire L1 and L2 translation lecturers in translator training to consider the evaluation methods they use carefully and refine the L2 translation curriculum based on solid evaluations and contrastive empirical research. Description: Ph.D.(KU Leuven)

2024-01-01T00:00:00Z Spiteri Miggiani, Giselle https://www.um.edu.mt/library/oar/handle/123456789/148214 2026-07-23T10:25:15Z 2026-01-01T00:00:00Z

Title: The role of language specialists in AI-dubbing workflows. Redefining skills and competencies Authors: Spiteri Miggiani, Giselle Abstract: The integration of artificial intelligence (AI) technologies is transforming workflows and creating new scenarios within the language services industry, demanding the development of new skills and competencies among professionals. This position paper provides an overview of the evolving profile of language specialists in AI-mediated dubbing and voice-over processes. It examines client expectations, specific tasks assigned to translation and language professionals, and the implications for training programs and curriculum development. To this end, an AI dubbing linguist competence profile is proposed, informed by tool experimentation, stakeholder conversations, and observations of industry dynamics from practitioner, trainer, and researcher perspectives. This profile aims to offer insights to language service providers (LSPs), tech developers, academic trainers, and both aspiring and practicing language professionals seeking to navigate this evolving landscape. By identifying the nuanced, creative, and cross-disciplinary responsibilities of linguists in AI-driven workflows, the paper aims to dispel any misconceptions that such solutions diminish the role of the linguist/translator. Instead, it points to an expanded and more nuanced professional profile requiring multi-layered expertise across domains, positioning linguists as key contributors to these hybrid dubbing processes.

2026-01-01T00:00:00Z Spiteri Miggiani, Giselle https://www.um.edu.mt/library/oar/handle/123456789/148213 2026-07-23T10:15:44Z 2026-01-01T00:00:00Z

Title: Quality in interlingual AI dubbing : exploring machine and human intersections Authors: Spiteri Miggiani, Giselle Abstract: The emergence and increasing prevalence of AI-driven end-to-end dubbing solutions necessitate an investigation into the quality of the generated output. This article offers an exploration of the intersections between machine output and human intervention in the production of AI-driven dubs, while identifying the nature of necessary human actions within the current state of the art. To this end, the article shares insights drawn from two independent exploratory studies carried out in training settings. First, an English AI dub, generated for didactic purposes, was evaluated and rated against its official studio-recorded counterpart. This served as a preliminary pilot application of the Script, Speech, and Sound (SSS) quality assessment framework (Spiteri Miggiani, 2024) across diverse training environments. Second, another experiment evaluated, rated, and compared the output of three different Italian AIdubbed versions of the same original clip, generated by three different platforms. The studio version was also evaluated as a benchmark. Issues were identified and labeled, and the specific “actions” required from human linguists were identified and categorized. While acknowledging that these findings are tool-dependent, context-specific, and subject to change as technology evolves, both cases nevertheless reveal consistent patterns where machine outputs intersect with human linguistic judgment. The key areas where human expertise appears to be essential include synchronization, voice consistency and expressiveness, narrative and semiotic cohesion, sound design, and language and translation.

2026-01-01T00:00:00Z