INVESTIGATING NEURAL MACHINE TRANSLATION QUALITY: AN XCOMET-XL-BASED ANALYSIS ACROSS KATHARINA REISS’S TEXT TYPOLOGIES
ENGLISH STUDIES AT NBU, cilt.12, sa.1, ss.196-219, 2026 (ESCI)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 12 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.33919/esnbu.26.1.12
- Dergi Adı: ENGLISH STUDIES AT NBU
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Central & Eastern European Academic Source (CEEAS), Linguistic Bibliography, MLA - Modern Language Association Database, Directory of Open Access Journals, MLA International Bibliography
- Sayfa Sayıları: ss.196-219
- Ondokuz Mayıs Üniversitesi Adresli: Evet
Özet
This study examines AI-driven neural methods that reduce human involvement in machine translation evaluation. Traditional evaluation approaches face challenges related to consistency, scalability, and evaluator subjectivity. To address these limitations, the study employs xCOMET-XL, which evaluates translation quality within a shared semantic space. Within the scope of this study, fifteen Turkish source texts, classified according to Katharina Reiss’s typology as informative, expressive, and operative, were translated into English using Google Translate and DeepL. The translations were evaluated using xCOMETXL, followed by human evaluation. The originality of the study lies in its comparative design examining the alignment between xCOMET-XL scores and human judgments. After comparing results, alignment between the methods was analysed. Findings signal a relatively high degree of alignment with human judgments in certain texts, highlighting neural metrics' potential as a fast, scalable, and systematic alternative. The study contributes to Translation Studies by supporting alternative translation evaluation approaches. Keywords: machine translation, xCOMET-XL, translation assessment, text types, Katharina Reiss