Translation Evaluation of Social Media Auto-Translate Feature toward News Headline
Abstract
Machine translation has become an everyday part of society's news consumption patterns. Unfortunately, important news content is poorly mediated by social media, especially on the output of the translation system feature on the site. Therefore, further research is needed on the evaluation of the auto-translate system on social media. This study focuses on the results of linguistic evaluation on the output of social media machine translation in translating news headlines. The data were taken from news coverage by the Reuters channel in the period of September 1st–7th, 2023 and from social media such as Facebook and Twitter. The translation evaluation used linguistic elements consisting of orthography, morphology, lexical, semantic, and syntax. This study found various kinds of linguistic non-equivalence. Orthographic non-equivalence includes punctuation, capitalization, and apostrophes. Morphological non-equivalence in the two systems was found in number concordance, inflection, derivation, and compounding. Lexical errors occur in both systems in the form of no correspondence and missing target words, as well as untranslated words and proper noun. In terms of semantics, both systems had difficulties with polysemy, homonymy, and expression. Finally, syntactic errors occur with missing articles, prepositions, and inappropriate arrangements of syntactic elements.
Copyright (c) 2024 Sasdaya: Gadjah Mada Journal of Humanities
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Sasdaya: Gadjah Mada Journal of Humanities applies the Creative Commons Attribution-ShareAlike 4.0 International License, with the copyright on the published articles held by the journal. Authors are required to transmit the copyright to this journal once the articles are accepted. This journal is granted a non-exclusive license to publish the articles as the original publisher, along with the commercial right to publish printed issues for sale. Since this journal applies an open-access mode, authors may post articles published by this journal on personal websites or institutional repositories both prior to and after publication while providing bibliographic details that credit this journal.
By publishing with this journal, the copyright holder grants any third party the lawful right to use their published article to the extent provided by the Creative Commons Attribution-ShareAlike 4.0 International license.
Subsequently, people are lawfully permitted to share, distribute, remix, adapt, and build upon the published articles, even for commercial purposes, so long as they provide appropriate credit or attribution (Title, Author, Source, and License of the work), include a link to the license, indicate if any changes were made, and redistribute the derivative outputs under the same license (CC BY-SA 4.0).
