Joon-Young Jung
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joon-Young Jung has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Dong-Oh Kang
Electronics and Telecommunications Research Institute
3 shared publications - Jang-Ho Choi2 shared publications
Changseok Bae
1 shared publication- Changseok Bae
Electronics and Telecommunications Research Institute
1 shared publication - Changseok Bae
Daejeon University, Daejeon, Republic of Korea
1 shared publication - Daewon Kim
Department of Semiconductor Engineering, Kyung Hee University, 1732 Deogyeong-daero, Giheung-gu, Yongin 17104, Republic of Korea
1 shared publication
Latest Publications
- 28 February 2024
- Published by Wiley in ETRI Journal
- Vol. 46 (1) , 35-47
CR‐M‐SpanBERT: Multiple embedding‐based DNN coreference resolution using self‐attention SpanBERT
This study introduces CR‐M‐SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding‐based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost‐effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR‐M‐SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high‐recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.
- 28 February 2024
- Published by Wiley in ETRI Journal
- Vol. 46 (1) , 35-47
CR‐M‐SpanBERT: Multiple embedding‐based DNN coreference resolution using self‐attention SpanBERT
This study introduces CR‐M‐SpanBERT, a coreference resolution (CR) model that utilizes multiple embedding‐based span bidirectional encoder representations from transformers, for antecedent recognition in natural language (NL) text. Information extraction studies aimed to extract knowledge from NL text autonomously and cost‐effectively. However, the extracted information may not represent knowledge accurately owing to the presence of ambiguous entities. Therefore, we propose a CR model that identifies mentions referring to the same entity in NL text. In the case of CR, it is necessary to understand both the syntax and semantics of the NL text simultaneously. Therefore, multiple embeddings are generated for CR, which can include syntactic and semantic information for each word. We evaluate the effectiveness of CR‐M‐SpanBERT by comparing it to a model that uses SpanBERT as the language model in CR studies. The results demonstrate that our proposed deep neural network model achieves high‐recognition accuracy for extracting antecedents from NL text. Additionally, it requires fewer epochs to achieve an average F1 accuracy greater than 75% compared with the conventional SpanBERT approach.
- Open Access
- 29 November 2021
- Published by Wiley in ETRI Journal
- Vol. 44 (3) , 438-449
DG‐based SPO tuple recognition using self‐attention M‐Bi‐LSTM
- 29 November 2021
- Published by Wiley in ETRI Journal
- Vol. 44 (3) , 438-449
Open AccessDG‐based SPO tuple recognition using self‐attention M‐Bi‐LSTM
- 15 February 2018
- Published by Wiley in ETRI Journal
- Vol. 40 (1) , 122-132
Spatial Region Estimation for Autonomous CoT Clustering Using Hidden Markov Model
- 15 February 2018
- Published by Wiley in ETRI Journal
- Vol. 40 (1) , 122-132
Spatial Region Estimation for Autonomous CoT Clustering Using Hidden Markov Model
- 1 April 2015
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 5 (2) , 132-136
Clustering Approach of Device Interactions for Automatic Generation of Device Social Relation
- 1 April 2015
- Published by EJournal Publishing in International Journal of Machine Learning and Computing
- Vol. 5 (2) , 132-136
Clustering Approach of Device Interactions for Automatic Generation of Device Social Relation
- 1 February 2015
- Published by EJournal Publishing in International Journal of Future Computer and Communication
- Vol. 4 (1) , 7-12
Estimating Social Tie Strength for Autonomous D2D Collaborations
- 1 February 2015
- Published by EJournal Publishing in International Journal of Future Computer and Communication
- Vol. 4 (1) , 7-12
Estimating Social Tie Strength for Autonomous D2D Collaborations
- 1 January 2012
- Published by Springer Nature
- p. 277-283
An Analysis on Personalization Technologies of Policy Based Dynamic Power Management of a Server System
- 1 January 2012
- Published by Springer Nature
- p. 277-283
An Analysis on Personalization Technologies of Policy Based Dynamic Power Management of a Server System
- 1 November 2011
- Published by Springer Nature
- p. 565-573
Remote Presentation for M Screen Service in Virtualization System
- 1 November 2011
- Published by Springer Nature
- p. 565-573
Remote Presentation for M Screen Service in Virtualization System