Survey of Research on Curriculum Learning in Neural Machine Translation

Curriculum learning, as an emerging technology, has gradually attracted attention in recent years. It is in line with human learning habits, from simple to difficult, from shallow to deep. Its core idea is to allow the model to learn from simple and basic concepts, and gradually transition to more c...

Full description

Saved in:
Bibliographic Details
Main Author: HU Chunyue, SI Qintu, WANG Siriguleng
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2025-02-01
Series:Jisuanji kexue yu tansuo
Subjects:
Online Access:http://fcst.ceaj.org/fileup/1673-9418/PDF/2403008.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850216100651859968
author HU Chunyue, SI Qintu, WANG Siriguleng
author_facet HU Chunyue, SI Qintu, WANG Siriguleng
author_sort HU Chunyue, SI Qintu, WANG Siriguleng
collection DOAJ
description Curriculum learning, as an emerging technology, has gradually attracted attention in recent years. It is in line with human learning habits, from simple to difficult, from shallow to deep. Its core idea is to allow the model to learn from simple and basic concepts, and gradually transition to more complex and higher-level content. In the translation of neural machines, curriculum learning is a training strategy to help models learn in accordance with certain laws. Curriculum learning has been proven to accelerate the convergence of the model and improve the quality and stability of the model translation. This paper first introduces the definition and basic framework of curriculum learning from the perspective of machine learning, and further explores its application in the field of neural machine translation. Two approaches of curriculum learning, namely predefined curriculum learning and dynamic curriculum learning, are discussed in detail from the perspectives of sample difficulty evaluation and model training scheduling strategies. Predefined curriculum learning guides the model to gradually learn tasks from simple to complex by pre-determining the difficulty order of samples. In contrast, dynamic curriculum learning adjusts the difficulty of samples dynamically based on the model’s current learning state, offering a more flexible training approach. Additionally, this paper analyzes the future research trends of curriculum learning in neural machine translation and proposes three promising research directions.
format Article
id doaj-art-cf9e2d2a72d949bf91e77d9c08f4e1d3
institution OA Journals
issn 1673-9418
language zho
publishDate 2025-02-01
publisher Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
record_format Article
series Jisuanji kexue yu tansuo
spelling doaj-art-cf9e2d2a72d949bf91e77d9c08f4e1d32025-08-20T02:08:24ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182025-02-0119233434310.3778/j.issn.1673-9418.2403008Survey of Research on Curriculum Learning in Neural Machine TranslationHU Chunyue, SI Qintu, WANG Siriguleng0College of Computer Science and Technology, Inner Mongolia Normal University, Hohhot 010022, ChinaCurriculum learning, as an emerging technology, has gradually attracted attention in recent years. It is in line with human learning habits, from simple to difficult, from shallow to deep. Its core idea is to allow the model to learn from simple and basic concepts, and gradually transition to more complex and higher-level content. In the translation of neural machines, curriculum learning is a training strategy to help models learn in accordance with certain laws. Curriculum learning has been proven to accelerate the convergence of the model and improve the quality and stability of the model translation. This paper first introduces the definition and basic framework of curriculum learning from the perspective of machine learning, and further explores its application in the field of neural machine translation. Two approaches of curriculum learning, namely predefined curriculum learning and dynamic curriculum learning, are discussed in detail from the perspectives of sample difficulty evaluation and model training scheduling strategies. Predefined curriculum learning guides the model to gradually learn tasks from simple to complex by pre-determining the difficulty order of samples. In contrast, dynamic curriculum learning adjusts the difficulty of samples dynamically based on the model’s current learning state, offering a more flexible training approach. Additionally, this paper analyzes the future research trends of curriculum learning in neural machine translation and proposes three promising research directions.http://fcst.ceaj.org/fileup/1673-9418/PDF/2403008.pdfcurriculum learning; neural machine translation; difficulty measure; training schedule
spellingShingle HU Chunyue, SI Qintu, WANG Siriguleng
Survey of Research on Curriculum Learning in Neural Machine Translation
Jisuanji kexue yu tansuo
curriculum learning; neural machine translation; difficulty measure; training schedule
title Survey of Research on Curriculum Learning in Neural Machine Translation
title_full Survey of Research on Curriculum Learning in Neural Machine Translation
title_fullStr Survey of Research on Curriculum Learning in Neural Machine Translation
title_full_unstemmed Survey of Research on Curriculum Learning in Neural Machine Translation
title_short Survey of Research on Curriculum Learning in Neural Machine Translation
title_sort survey of research on curriculum learning in neural machine translation
topic curriculum learning; neural machine translation; difficulty measure; training schedule
url http://fcst.ceaj.org/fileup/1673-9418/PDF/2403008.pdf
work_keys_str_mv AT huchunyuesiqintuwangsiriguleng surveyofresearchoncurriculumlearninginneuralmachinetranslation