Jul 2026· The International Journal of Translation and Interpreting Research· 0 citations
TL;DR
Assessment of how GT and GPT-4o translate English VPE into Arabic focuses on the accuracy of ellipsis reconstruction and the translation strategies employed, highlighting the importance of better-quality training data for NMT and LLM tools for both discourse-level processing and context-dependent data.
Abstract
Verb phrase ellipsis (VPE) poses considerable challenges in translation from English into Arabic, especially when using automated systems where syntactic nuances are often unresolved. This study examines how Neural Machine Translation (NMT) tools and Large Language Models (LLM) process VPE in English-Arabic translation. Using Google Translate (GT) and ChatGPT-4o (GPT-4o) as representatives of each of these technologies, a dataset of 413 English sentences containing instances of VPE was translated into Arabic using both tools. Each output was then analyzed, focusing on accuracy and ellipsis recovery quality with a categorization of translation patterns used in rendering the VPE instances. This study aims to assess how GT and GPT-4o translate English VPE into Arabic, focusing on the accuracy of ellipsis reconstruction and the translation strategies employed. A quantitative comparative method was employed, supported by a frequency-based analysis to determine recurring patterns. The results revealed that both tools employed the same recovery patterns but with different frequencies. GT outperformed GPT-4o in overall accuracy, producing more consistent and contextually appropriate translations. GT successfully used modulation, lexical repetition, and substitution, while GPT-4o heavily used substitution but with many incomplete instances, indicating its lack of ability to make context-dependent inferences. The study underscores the importance of better-quality training data for NMT and LLM tools for both discourse-level processing and context-dependent data. This study offers insights into research on computational linguistics and machine translation with practical implications for translation software developers, Arabic language specialists, and researchers in machine translation assessment.
This study examines the extent to which machine-translated and human-translated Croatian–English phrases can be distinguished by expert evaluators by analysing inter-rater agreement. For this purpose, a parallel corpus was compiled from four Croatian research articles in the fields of Education and Psychology, together with their human translations and machine translations produced using the online tool onlinedoctranslator. com. Two professional translators, native speakers of Croatian with extensive translation experience, were asked to classify selected English translations of Croatian phrases as either machine-translated or human-translated. The analysis shows a raw inter-rater agreement of 75 % for both machine-translated and human-translated phrase sets, indicating a moderate level of agreement between the raters. These results suggest that even expert translators do not consistently reach the same conclusions when judging the origin of short, decontextualised translated phrases. The findings support the view that, at the phrase level, machine-translated output is increasingly difficult to distinguish from human translation on the basis of surface linguistic features alone.
Mirjana Borucinsky, Margareta Čanžar· Croatica et Slavica Iadertin...· 0 citations
This study investigates the translation of gender from English into Arabic, focusing on the performance of senior-level translation students in a literary context. Building on previous research on verbal and adjectival translation, the article adopts a mixed-methods approach combining quantitative frequency analysis with qualitative examination of error types. The corpus consists of selected passages from Naguib Mahfouz’s Midaq Alley, translated into Modern Standard Arabic by student translators. Gender-related renderings are classified as similar, different or unattempted in order to assess both accuracy and omission. The findings indicate that while gender is generally handled correctly at the lexical level, significant difficulties arise in maintaining agreement within phrases and clauses, particularly in cases involving inanimate or abstract nouns and structurally complex constructions. The study highlights the impact of grammatical asymmetry between English and Arabic on translation performance and underscores the need for more systematic instruction in contrastive grammar and contextual analysis. It contributes to a more nuanced understanding of gender as a key factor in English–Arabic literary translation and provides implications for translator training.
K. Mansoor, Daniel Dejica· Scientific Bulletin of the P...· 0 citations
Translation plays an important role in transferring meaning across languages, particularly when translating idiomatic expressions whose meanings cannot be interpreted literally. This study aimed to identify the translation strategies employed by sixth-semester students in translating English idiomatic expressions into Indonesian and to investigate the translation difficulties they encountered. The study employed a descriptive quantitative design involving 24 sixth-semester students of the English Department at UIN Fatmawati Sukarno Bengkulu. The research instrument was a translation test consisting of 15 idiomatic expressions selected from Barack Obama's speech Ignorance is Not a Virtue. The students' translations were analyzed using Baker's (1992) translation strategies, while translation difficulties were classified based on Baker (1992) and Larson (1998). The findings revealed that Translation by Paraphrase was the dominant strategy, accounting for 345 translations (95.83%), followed by Using an Idiom of Similar Meaning but Dissimilar Form with 15 translations (4.17%). No data were categorized as Using an Idiom of Similar Meaning and Form or Translation by Omission. Regarding translation difficulties, Contextual Difficulty was the most dominant category with 161 cases (73.85%), followed by Linguistic Difficulty with 33 cases (15.14%) and Cultural Difficulty with 24 cases (11.01%). The findings indicate that students experienced greater difficulty in interpreting the intended meanings of idiomatic expressions within their communicative contexts than in understanding linguistic or cultural aspects. Furthermore, 218 translations (60.55%) were classified as less accurate and inaccurate, indicating that contextual interpretation substantially influenced translation quality. The study suggests that translation instruction should emphasize contextual interpretation alongside linguistic and cultural competence to improve students' ability to translate idiomatic expressions accurately
This work contributes a preliminary cross-system comparison for an underexplored language pair and lays the groundwork for larger-scale evaluations of gender-inclusive AT, indicating that all four models struggle to faithfully convey gender information from source to target.
Xiaolan Xu, Sara Mendes, F. Batista et al.· 0 citations
This pilot study examines how the English adverb actually is rendered in Slovak translation, drawing on a corpus of literary texts and their translations. As a multifunctional item, actually performs a range of syntactic and pragmatic functions in context, most notably those of emphasizer and disjunct. The analysis draws on three Slovak translations of works by the same English-speaking author. Although each translator worked on a different set of books, the corpus still makes it possible to compare translation strategies within a relatively consistent authorial style and to observe how individual translators deal with the same multifunctional source item. The study combines qualitative functional analysis with quantitative observations in order to identify recurrent Slovak renderings of actually, including lexical substitution, structural reformulation, attenuation, and omission. The findings suggest that translation difficulty arises not from the lack of Slovak expressive resources, but from differences between English and Slovak in the grammatical encoding of discourse-related meaning. In particular, functions expressed in English through sentence adverbials do not always correspond to a single formal category in Slovak, which increases the likelihood of functional shift or translation loss. The study contributes to translation studies and contrastive linguistics by showing how the pragmatic contribution of a frequent multifunctional item may be preserved, reinterpreted, weakened, or omitted in translation, and how these outcomes vary across translators.
Zuzana Knižková· Studies About Languages· 0 citations
Background:
This mixed-method study investigates the effectiveness of integrating Google Translate (GT) and Grammarly as a combined English-for-Academic-Purposes (EAP) learning and teaching intervention, aiming to improve the accuracy, clarity, and readability of Indonesian-to-English academic texts.
Methodology:
The study employs a sequential explanatory design combining quantitative error analysis with qualitative expert feedback. Purposive sampling was used to select a 7,500-word corpus of published Indonesian academic articles across six disciplines: linguistics, technology, economics, engineering, medical science, and law. Six EAP instructors/translators with advanced IELTS scores served as raters. Machine-generated translations via GT were post-edited using Grammarly. Quantitative data consisted of 519 Grammarly-detected writing issues categorized into clarity, correctness, delivery, and engagement. Qualitative data were collected through open-ended questionnaires based on Machali’s Translation Quality Assessment rubric. Descriptive statistics and thematic coding were used for analysis.
Findings:
Grammarly post-editing reduced grammatical and stylistic errors by over 54% in correctness and 35% in clarity categories. However, human intervention remained essential for addressing semantic nuance and cultural appropriateness. Raters evaluated engineering and technology texts more favorably (mean score = 5.8/7) than linguistics texts (mean = 4.3/7), indicating domain-specific variation in translation quality.
Conclusion:
The integration of GT and Grammarly improves the overall quality of machine-translated academic texts, particularly in grammatical accuracy and clarity. Nevertheless, expert human involvement is still required to ensure semantic precision and contextual appropriateness for publication-ready outputs.
Originality:
This study introduces a practical way to combine Google Translate and Grammarly for EAP learning, while showing that human expertise is still essential for high-quality academic writing.
