Developing Language-Specific Models Using a Neural Architecture Search

This paper applies the neural architecture search (NAS) method to Korean and English grammaticality judgment tasks. Based on the previous research, which only discusses the application of NAS on a Korean dataset, we extend the method to English grammatical tasks and compare the resulting two archite...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: YongSuk Yoo, Kang-moon Park
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/c79334b89eb94989a5438a10f2e183a1
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:c79334b89eb94989a5438a10f2e183a1
record_format dspace
spelling oai:doaj.org-article:c79334b89eb94989a5438a10f2e183a12021-11-11T15:22:51ZDeveloping Language-Specific Models Using a Neural Architecture Search10.3390/app1121103242076-3417https://doaj.org/article/c79334b89eb94989a5438a10f2e183a12021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/10324https://doaj.org/toc/2076-3417This paper applies the neural architecture search (NAS) method to Korean and English grammaticality judgment tasks. Based on the previous research, which only discusses the application of NAS on a Korean dataset, we extend the method to English grammatical tasks and compare the resulting two architectures from Korean and English. Since complex syntactic operations exist beneath the word order that is computed, the two different resulting architectures out of the automated NAS language modeling provide an interesting testbed for future research. To the extent of our knowledge, the methodology adopted here has not been tested in the literature. Crucially, the resulting structure of the NAS application shows an unexpected design for human experts. Furthermore, NAS has generated different models for Korean and English, which have different syntactic operations.YongSuk YooKang-moon ParkMDPI AGarticledeep learningneural architecture searchword orderingKorean syntaxTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10324, p 10324 (2021)
institution DOAJ
collection DOAJ
language EN
topic deep learning
neural architecture search
word ordering
Korean syntax
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle deep learning
neural architecture search
word ordering
Korean syntax
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
YongSuk Yoo
Kang-moon Park
Developing Language-Specific Models Using a Neural Architecture Search
description This paper applies the neural architecture search (NAS) method to Korean and English grammaticality judgment tasks. Based on the previous research, which only discusses the application of NAS on a Korean dataset, we extend the method to English grammatical tasks and compare the resulting two architectures from Korean and English. Since complex syntactic operations exist beneath the word order that is computed, the two different resulting architectures out of the automated NAS language modeling provide an interesting testbed for future research. To the extent of our knowledge, the methodology adopted here has not been tested in the literature. Crucially, the resulting structure of the NAS application shows an unexpected design for human experts. Furthermore, NAS has generated different models for Korean and English, which have different syntactic operations.
format article
author YongSuk Yoo
Kang-moon Park
author_facet YongSuk Yoo
Kang-moon Park
author_sort YongSuk Yoo
title Developing Language-Specific Models Using a Neural Architecture Search
title_short Developing Language-Specific Models Using a Neural Architecture Search
title_full Developing Language-Specific Models Using a Neural Architecture Search
title_fullStr Developing Language-Specific Models Using a Neural Architecture Search
title_full_unstemmed Developing Language-Specific Models Using a Neural Architecture Search
title_sort developing language-specific models using a neural architecture search
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/c79334b89eb94989a5438a10f2e183a1
work_keys_str_mv AT yongsukyoo developinglanguagespecificmodelsusinganeuralarchitecturesearch
AT kangmoonpark developinglanguagespecificmodelsusinganeuralarchitecturesearch
_version_ 1718435392656506880