Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study
With the wide application of artificial intelligence represented by deep learning in natural language-processing tasks, the automated scoring of translations has also advanced and improved. This study aims to determine if the BERT-assist system can reliably assess translation quality and identify hi...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2024-02-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/14/5/1925 |
_version_ | 1797264833010204672 |
---|---|
author | Yizhuo Cui Maocheng Liang |
author_facet | Yizhuo Cui Maocheng Liang |
author_sort | Yizhuo Cui |
collection | DOAJ |
description | With the wide application of artificial intelligence represented by deep learning in natural language-processing tasks, the automated scoring of translations has also advanced and improved. This study aims to determine if the BERT-assist system can reliably assess translation quality and identify high-quality translations for potential recognition. It takes the Han Suyin International Translation Contest as a case study, which is a large-scale and influential translation contest in China, with a history of over 30 years. The experimental results show that the BERT-assist system is a reliable second rater for massive translations in terms of translation quality, as it can effectively sift out high-quality translations with a reliability of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>r</mi></semantics></math></inline-formula> = 0.9 or higher. Thus, the automated translation scoring system based on BERT can satisfactorily predict the ranking of translations according to translation quality and sift out high-quality translations potentially shortlisted for prizes. |
first_indexed | 2024-04-25T00:35:11Z |
format | Article |
id | doaj.art-2fa36db229b84eb08f65bb8a9cf1c24e |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-04-25T00:35:11Z |
publishDate | 2024-02-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-2fa36db229b84eb08f65bb8a9cf1c24e2024-03-12T16:39:29ZengMDPI AGApplied Sciences2076-34172024-02-01145192510.3390/app14051925Automated Scoring of Translations with BERT Models: Chinese and English Language Case StudyYizhuo Cui0Maocheng Liang1School of Humanities and Law, North China University of Technology, Beijing 100144, ChinaSchool of Foreign Languages, Beihang University, Beijing 100191, ChinaWith the wide application of artificial intelligence represented by deep learning in natural language-processing tasks, the automated scoring of translations has also advanced and improved. This study aims to determine if the BERT-assist system can reliably assess translation quality and identify high-quality translations for potential recognition. It takes the Han Suyin International Translation Contest as a case study, which is a large-scale and influential translation contest in China, with a history of over 30 years. The experimental results show that the BERT-assist system is a reliable second rater for massive translations in terms of translation quality, as it can effectively sift out high-quality translations with a reliability of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>r</mi></semantics></math></inline-formula> = 0.9 or higher. Thus, the automated translation scoring system based on BERT can satisfactorily predict the ranking of translations according to translation quality and sift out high-quality translations potentially shortlisted for prizes.https://www.mdpi.com/2076-3417/14/5/1925large language modelBERTautomated scoring of translationslarge-scale translation contest |
spellingShingle | Yizhuo Cui Maocheng Liang Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study Applied Sciences large language model BERT automated scoring of translations large-scale translation contest |
title | Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study |
title_full | Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study |
title_fullStr | Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study |
title_full_unstemmed | Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study |
title_short | Automated Scoring of Translations with BERT Models: Chinese and English Language Case Study |
title_sort | automated scoring of translations with bert models chinese and english language case study |
topic | large language model BERT automated scoring of translations large-scale translation contest |
url | https://www.mdpi.com/2076-3417/14/5/1925 |
work_keys_str_mv | AT yizhuocui automatedscoringoftranslationswithbertmodelschineseandenglishlanguagecasestudy AT maochengliang automatedscoringoftranslationswithbertmodelschineseandenglishlanguagecasestudy |