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...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/21/10324 |
| _version_ | 1827678266615398400 |
|---|---|
| author | YongSuk Yoo Kang-moon Park |
| author_facet | YongSuk Yoo Kang-moon Park |
| author_sort | YongSuk Yoo |
| collection | DOAJ |
| 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. |
| first_indexed | 2024-03-10T06:06:54Z |
| format | Article |
| id | doaj.art-c79334b89eb94989a5438a10f2e183a1 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T06:06:54Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c79334b89eb94989a5438a10f2e183a12023-11-22T20:31:22ZengMDPI AGApplied Sciences2076-34172021-11-0111211032410.3390/app112110324Developing Language-Specific Models Using a Neural Architecture SearchYongSuk Yoo0Kang-moon Park1Department of English Literature, College of Humanities, Jeonbuk National University, Jeonju-si 54896, KoreaDepartment of Elctronic Engineering, Korea National University of Transportation, Chungju 27469, Chungcheongbuk-do, KoreaThis 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.https://www.mdpi.com/2076-3417/11/21/10324deep learningneural architecture searchword orderingKorean syntax |
| spellingShingle | YongSuk Yoo Kang-moon Park Developing Language-Specific Models Using a Neural Architecture Search Applied Sciences deep learning neural architecture search word ordering Korean syntax |
| title | 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_short | Developing Language-Specific Models Using a Neural Architecture Search |
| title_sort | developing language specific models using a neural architecture search |
| topic | deep learning neural architecture search word ordering Korean syntax |
| url | https://www.mdpi.com/2076-3417/11/21/10324 |
| work_keys_str_mv | AT yongsukyoo developinglanguagespecificmodelsusinganeuralarchitecturesearch AT kangmoonpark developinglanguagespecificmodelsusinganeuralarchitecturesearch |