EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Investigating neural machine translation quality: An xCOMET-XL-based analysis across Katharina Reiss's text typologies

Betül Özcan Dost

English Studies at NBU · 20.06.2026 · 12 (1) · 196

DOI: 10.33919/esnbu.26.1.12 ↗

Kurz gefasst

Fachartikel in der Zeitschrift English Studies at NBU, online erschienen am 20.06.2026. Verfasst von Betül Özcan Dost. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 xCOMET-XL, 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.

Zitieren

APA

Dost, B. Ö. (2026). Investigating neural machine translation quality: An xCOMET-XL-based analysis across Katharina Reiss's text typologies. English Studies at NBU, 12(1), 196. https://doi.org/10.33919/esnbu.26.1.12

Vancouver

Dost BÖ. Investigating neural machine translation quality: An xCOMET-XL-based analysis across Katharina Reiss's text typologies. English Studies at NBU. 2026;12(1):196. doi:10.33919/esnbu.26.1.12

BibTeX
@article{Dost2026,
  author = {Dost, Betül Özcan},
  title = {Investigating neural machine translation quality: An xCOMET-XL-based analysis across Katharina Reiss's text typologies},
  journal = {English Studies at NBU},
  year = {2026},
  volume = {12},
  number = {1},
  pages = {196},
  doi = {10.33919/esnbu.26.1.12}
}
Kostenlos starten →