Izvorni znanstveni članak
https://doi.org/10.15291/csi.5069
Detection of Machine-Translated Croatian-English Phrases: Do Translators Agree in their Assessment?
Mirjana Borucinsky
orcid.org/0000-0002-1132-9720
; Faculty of Maritime Studies, University of Rijeka, Croatia
*
Margareta Čanžar
; Faculty of Humanities and Social Sciences, University of Rijeka, Croatia
*
* Dopisni autor.
Sažetak
This study examines the extent to which machine-translat-
ed 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 Educa-
tion and Psychology, together with their human translations
and machine translations produced using the online tool on-
linedoctranslator.com. Two professional translators, native
speakers of Croatian with extensive translation experience,
were asked to classify selected English translations of Cro-
atian phrases as either machine-translated or human-trans-
lated. 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 be-
tween 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.
Ključne riječi
Croatian-English; human evaluation; inter-rater agreement; machine translation
Hrčak ID:
349366
URI
Datum izdavanja:
14.7.2026.
Posjeta: 0 *