THE COMPARISON IN NATURALNESS OF POST-EDITING TRANSLATION ON GOOGLE NMT AND YANDEX NMT BY ENGLISH DEPARTMENT STUDENTS

AZZA RABIATUL, ADAWIYAH (2023) THE COMPARISON IN NATURALNESS OF POST-EDITING TRANSLATION ON GOOGLE NMT AND YANDEX NMT BY ENGLISH DEPARTMENT STUDENTS. S1 thesis, Universitas Mataram.

[img] Text
REVISI SIDANG AZZA (1).pdf
Restricted to Repository staff only
Download (1MB)
[img]
Preview
 Text
ARTIKEL AZZA.pdf
Download (306kB) | Preview

Abstract

This study aims to examine the naturalness of post-editing translations using Google NMT and Yandex NMT by English Department students and to determine which of the two NMT tools came closest to the naturalness of a short story's translation. This study's subjects were local English Language Education students at the University of Mataram. Meanwhile, the object of this study was an English short story entitled "Jack and the Beanstalk." In this study, researchers used Larson's theory as a research reference to analyze the naturalness of English-toIndonesian translations in the short story Jack and the Beanstalk. Data were obtained through two data collection methods: observation and documentation, which were carried out in class 5TI-1, IT-based translation class. The total data for this study were 1248 sentences analyzed descriptively. The study showed the percentage of text quality in natural translation students achieved when postediting. In GNMT, most of the post-editing quality is “highly natural” with 88%, followed by “natural” with 5%, “less natural” with 6%, and “unnatural” with 1%. On the other hand, a few differences were found in the percentage of post-editing results in YNMT, which shows post-editing quality in “highly natural” with 81%, followed by “natural” with 6%, “less natural” with 8%, and “unnatural” with 4%. Therefore, the study concludes that the quality of naturalness of the translation in post-editing from GNMT produces better-translated text than YNMT

Item Type: Thesis (S1)
Keywords (Kata Kunci): Google Neural Machine Translation, Yandex Neural Machine Translation, naturalness, post-editing, short story
Subjects: L Education > LC Special aspects of education > LC5201 Education extension. Adult education. Continuing education
Divisions: Fakultas Keguruan dan Ilmu Pendidikan
Depositing User: Meike Megawati
Date Deposited: 19 May 2023 06:04
Last Modified: 19 May 2023 06:04
URI: http://eprints.unram.ac.id/id/eprint/38078

Actions (login required)

View Item View Item
Repository UNRAM is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.