Zobrazeno 1 - 10 of 88 pro vyhledávání: '"Seung Hoon Na"'
1
Akademický článek
Transformer-based reranking for improving Korean morphological analysis systems
Autor: Jihee Ryu, Soojong Lim, Oh-Woog Kwon, Seung-Hoon Na
Publikováno v: ETRI Journal, Vol 46, Iss 1, Pp 137-153 (2024)
This study introduces a new approach in Korean morphological analysis combining dictionary-based techniques with Transformer-based deep learning models. The key innovation is the use of a BERT-based reranking system, significantly enhancing the accur
Externí odkaz: https://doaj.org/article/cbc3e98b1703412a8679ef5877ec41f1
Zobrazit plný text záznamu
2
Akademický článek
Special issue on speech and language AI technologies
Autor: Dong-Jin Kim, Hyung-Min Park, Harksoo Kim, Seung-Hoon Na, Gerard J. Kim
Publikováno v: ETRI Journal, Vol 46, Iss 1, Pp 7-10 (2024)
Externí odkaz: https://doaj.org/article/dde9879404264ef6af5c886a4a826c4b
Zobrazit plný text záznamu
3
Akademický článek
Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs
Autor: Wafa Shafqat, Seung-Hoon Na
Publikováno v: Applied Sciences, Vol 14, Iss 4, p 1508 (2024)
In today’s world, where information keeps growing rapidly and changing constantly, language models play a crucial role in making our lives easier across different fields. However, it is tough to keep these models updated with all the new data while
Externí odkaz: https://doaj.org/article/bdbb28bf43f0410a8a223002ab9a9521
Zobrazit plný text záznamu
4
Akademický článek
MultiFusedNet: A Multi-Feature Fused Network of Pretrained Vision Models via Keyframes for Student Behavior Classification
Autor: Somsawut Nindam, Seung-Hoon Na, Hyo Jong Lee
Publikováno v: Applied Sciences, Vol 14, Iss 1, p 230 (2023)
This research proposes a deep learning method for classifying student behavior in classrooms that follow the professional learning community teaching approach. We collected data on five student activities: hand-raising, interacting, sitting, turning
Externí odkaz: https://doaj.org/article/132ff405e8534685bad02003b76dffc4
Zobrazit plný text záznamu
9
Uniformly Interpolated Balancing for Robust Prediction in Translation Quality Estimation
Autor: Hyun Kim, Seung-Hoon Na
Publikováno v: ACM Transactions on Asian and Low-Resource Language Information Processing. 19:1-27
There has been growing interest among researchers in quality estimation (QE), which attempts to automatically predict the quality of machine translation (MT) outputs. Most existing works on QE are based on supervised approaches using quality-annotate
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d8ba41c3a894e820b00706ae9fde395a
https://doi.org/10.1145/3365916
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje