View in EDS PDF Full Text

A Pilot Study of Multi-Method Evaluation of Machine Translation in Macedonian.

Saved in:
Bibliographic Details
Title: A Pilot Study of Multi-Method Evaluation of Machine Translation in Macedonian.
Authors: Jana, Kuzmanova1 jana.kuzmanova@finki.ukim.mk, Katerina, Zdravkova1 katerina.zdravkova@finki.ukim.mk
Source: Computer Science & Information Systems. Apr2026, Vol. 23 Issue 2, p827-859. 33p.
Subjects: Evaluation methodology, Machine translating, Low-resource languages, Translating & interpreting, Slavic languages, Generative pre-trained transformers, Linguistic analysis
Abstract: This pilot study offers a linguistic evaluation of six machine translation systems: GPT-4o, GPT-5, Gemini 2.5 Flash, Google Translate, Microsoft Translator, and NLLB-600M applied to the translation of a short excerpt of Orwell’s "1984" into Macedonian. The analysis consisted of three interconnected experiments: manual annotation of translation errors and comparison with human output, evaluation using eight popular MT metrics, and sentence-level similarity analysis via cosine similarity, Jaccard similarity, and Levenshtein distance. Manual annotation revealed that stylistic errors (48.47%) and linguistic errors (34.54%) were the most common. The LLMs outperformed other systems, particularly GPT-5, while NLLB-600M performed poorly, often introducing incomprehensible sentences or non-existent words. Metrics-based evaluation showed that lexical metrics sometimes penalized fluent and accurate translations that deviated from the reference. Sentence similarity analysis confirmed that accurate translations were more consistent, while wrong–wrong sentence pairs were more divergent, especially in Levenshtein scores. The findings underscore the importance of combining manual and metric-based evaluation to fully understand MT quality, particularly in low-resource settings. [ABSTRACT FROM AUTHOR]
Copyright of Computer Science & Information Systems is the property of ComSIS Consortium and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 193328682
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A Pilot Study of Multi-Method Evaluation of Machine Translation in Macedonian.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Jana%2C+Kuzmanova%22">Jana, Kuzmanova</searchLink><relatesTo>1</relatesTo><i> jana.kuzmanova@finki.ukim.mk</i><br /><searchLink fieldCode="AR" term="%22Katerina%2C+Zdravkova%22">Katerina, Zdravkova</searchLink><relatesTo>1</relatesTo><i> katerina.zdravkova@finki.ukim.mk</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Computer+Science+%26+Information+Systems%22">Computer Science & Information Systems</searchLink>. Apr2026, Vol. 23 Issue 2, p827-859. 33p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Evaluation+methodology%22">Evaluation methodology</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+translating%22">Machine translating</searchLink><br /><searchLink fieldCode="DE" term="%22Low-resource+languages%22">Low-resource languages</searchLink><br /><searchLink fieldCode="DE" term="%22Translating+%26+interpreting%22">Translating & interpreting</searchLink><br /><searchLink fieldCode="DE" term="%22Slavic+languages%22">Slavic languages</searchLink><br /><searchLink fieldCode="DE" term="%22Generative+pre-trained+transformers%22">Generative pre-trained transformers</searchLink><br /><searchLink fieldCode="DE" term="%22Linguistic+analysis%22">Linguistic analysis</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This pilot study offers a linguistic evaluation of six machine translation systems: GPT-4o, GPT-5, Gemini 2.5 Flash, Google Translate, Microsoft Translator, and NLLB-600M applied to the translation of a short excerpt of Orwell’s "1984" into Macedonian. The analysis consisted of three interconnected experiments: manual annotation of translation errors and comparison with human output, evaluation using eight popular MT metrics, and sentence-level similarity analysis via cosine similarity, Jaccard similarity, and Levenshtein distance. Manual annotation revealed that stylistic errors (48.47%) and linguistic errors (34.54%) were the most common. The LLMs outperformed other systems, particularly GPT-5, while NLLB-600M performed poorly, often introducing incomprehensible sentences or non-existent words. Metrics-based evaluation showed that lexical metrics sometimes penalized fluent and accurate translations that deviated from the reference. Sentence similarity analysis confirmed that accurate translations were more consistent, while wrong–wrong sentence pairs were more divergent, especially in Levenshtein scores. The findings underscore the importance of combining manual and metric-based evaluation to fully understand MT quality, particularly in low-resource settings. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Computer Science & Information Systems is the property of ComSIS Consortium and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=193328682
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.2298/CSIS251020021K
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 33
        StartPage: 827
    Subjects:
      – SubjectFull: Evaluation methodology
        Type: general
      – SubjectFull: Machine translating
        Type: general
      – SubjectFull: Low-resource languages
        Type: general
      – SubjectFull: Translating & interpreting
        Type: general
      – SubjectFull: Slavic languages
        Type: general
      – SubjectFull: Generative pre-trained transformers
        Type: general
      – SubjectFull: Linguistic analysis
        Type: general
    Titles:
      – TitleFull: A Pilot Study of Multi-Method Evaluation of Machine Translation in Macedonian.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Jana, Kuzmanova
      – PersonEntity:
          Name:
            NameFull: Katerina, Zdravkova
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 18200214
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Computer Science & Information Systems
              Type: main
ResultId 1