Repository logo

D-Repository

Alsun

Permanent URI for this communityhttps://iorep.miuegypt.edu.eg/handle/20.500.13071/9

Browse

Browsing Alsun by Issue Date

Filter results by year or month
Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemRestricted
    Machine translation output for Arabic-to-English translation of legal texts : A comparative study between AI Tools /
    Reda, Dalia Ehab Abdulaziz,; Supervisor : Mustafa Riad, Sama Dawood. Includes Arabic Summary.
    The effectiveness of machine translation (MT) in the legal domain requires close evaluation using appropriate quality assessment models. This study assesses the translation quality of two advanced MT systems, Gemini and ChatGPT by analyzing their English translations of three Arabic Memorandums of Association. The TAUS Dynamic Quality Framework (DQF) was adopted as the primary evaluation metric, with a focus on error typology and frequency to measure translation performance. The research adopts a quantitative approach, examining the outputs in terms of accuracy and fluency, while identifying and categorizing errors. A total of 1,022 errors were recorded and analyzed: 425 in ChatGPT translations and 597 in Gemini. The findings indicate distinct tendencies in each system: ChatGPT often omits source text content, while Gemini exhibits a tendency toward over-translation. ChatGPT’s output showed a higher percentage of accuracy-related errors, particularly mistranslations, whereas Gemini was more prone to over translation errors. The study underscores the ongoing necessity of human post-editing in legal translation workflows. It also emphasizes the importance of incorporating domain-specific training data and tailored quality assurance (QA) modules to improve MT output in legal contexts. Ultimately, this research contributes to the growing body of literature on MT evaluation by offering insight into the strengths, limitations, and error patterns of emerging AI-powered translation tools. The researcher recommends further exploration of additional TAUS error categories, such as style and locale, and calls for broader experimentation with other MT systems to reflect the rapid development of AI in legal translation. Keywords: Machine Translation, Legal Translation, Neural Machine Translation, TAUS Error Typology, ChatGPT, Gemini.
  • Thumbnail Image
    ItemRestricted
    Machine vs. human translation of cultural dimensions in children’s literature : Andersen and Rowling as Cases of Study /
    Saleeb, Sandy Adel Nabih Rizk,; Supervisor : Fadwa Kamal, Sama Dawood. Includes Arabic Summary.
    This comparative study investigates the efficacy of Machine Translation (MT) in translating children’s literature, specifically examining its treatment of cultural references. The selected genres for analysis are fantasy fiction and fairy tales fiction. Accordingly, the study includes short stories by Hans Christian Andersen alongside the third book in the Harry Potter series, Harry Potter and the Prisoner of Azkaban, by J. K. Rowling. By employing a comparative and contrastive approach, the MT output, generated by ChatGPT, is analyzed against human translations. The findings offer valuable insights into the effectiveness of MT in preserving cultural identity in children's literature. The results reveal that while ChatGPT tends to produce literal translations with minimal cultural filtering, human translators employ adaptive strategies such as omission, substitution, and compensation to maintain cultural relevance. The study concludes that although MT tools are rapidly advancing, they still require human oversight to handle culturally sensitive content, particularly in texts intended for young audiences. This research ends with practical recommendations for translators, NLP engineers, and future scholars to enhance culturally aware MT systems in the Arab context. Keywords: Machine Translation, Children’s Literature, Cultural Appropriation, Fantasy, Fairy
  • Thumbnail Image
    ItemRestricted
    Quality assessment of ChatGPT and Gemini English into Arabic translation in the domain of climate change : A comparative study /
    El-Outify, Yara Tarek,; Supervisor : Mustafa Riad, Maha Fathi, Hanan Sharaf El-Dine. Includes Arabic Summary.
  • Thumbnail Image
    ItemRestricted
    The impact of using bionic font in speech-to-text Tools on the accuracy of English into Arabic interpretation /
    Elhefny, Rawan Hesham,; Supervisor : Bahaa eddin M. Mazid, Ingy Farouk Emara. Includes Arabic Summary.
    Consecutive interpreting (CI) requires significant cognitive effort, with interpreters juggling listening, note-taking, and verbal output in real time. This study investigates whether the Bionic Reading font, designed to enhance reading efficiency, could reduce cognitive load and improve accuracy in Arabic CI tasks. It aims to determine whether the Bionic Reading font could optimize the user experience of Speech-to-Text (STT) tools, leading to reduced cognitive load and improved CI accuracy. A quasi-experimental design is used, with participants (n=5) engaging in an interpreting task under both font conditions. Pre- and post-test questionnaires evaluates readability, processing speed, comprehension, comfort, interpreting accuracy, cognitive load, and font preference. Performance is further analyzed using Daniel Gile’s Effort Model, which provided a framework for assessing cognitive strain, and through Errors, Omissions, and Infelicities (EOI) analysis, which offers a systematic means of evaluating interpreting quality. The findings infoms the development of user-friendly STT tools with customizable font options, offering practical implications for enhancing communication accessibility and effectiveness, and laying the groundwork for further exploration of this technology’s potential across languages.