Evolutionary Neural Architecture Search (NAS) Using Chromosome Non-Disjunction for Korean Grammaticality Tasksopen access
- Authors
- Park, Kang-moon; Shin, Donghoon; Yoo, Yongsuk
- Issue Date
- May-2020
- Publisher
- MDPI
- Keywords
- Deep learning; Korean syntax; Neural architecture search; Word ordering
- Citation
- Applied Sciences-basel, v.10, no.10
- Journal Title
- Applied Sciences-basel
- Volume
- 10
- Number
- 10
- URI
- https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151523
- DOI
- 10.3390/app10103457
- ISSN
- 2076-3417
- Abstract
- Featured Application,Neural Architecture Search (NAS) on linguistic tasks.,Abstract In this paper, we apply the neural architecture search (NAS) method to Korean grammaticality judgment tasks. Since the word order of a language is the final result of complex syntactic operations, a successful neural architecture search in linguistic data suggests that NAS can automate language model designing. Although NAS application to language has been suggested in the literature, we add a novel dataset that contains Korean-specific linguistic operations, which adds great complexity in the patterns. The result of the experiment suggests that NAS provides an architecture for the language. Interestingly, NAS has suggested an unprecedented structure that would not be designed manually. Research on the final topology of the architecture is the topic of our future research.,
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 공과대학 > 기계시스템학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151523)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.