no code implementations • 2 May 2023 • DongNyeong Heo, Heeyoul Choi
Latent variable modeling in non-autoregressive neural machine translation (NAT) is a promising approach to mitigate the multimodality problem.
no code implementations • 19 Jan 2023 • Namjin Seo, DongNyeong Heo, Heeyoul Choi
Network function virtualization (NFV) and software-defined network (SDN) have become emerging network paradigms, allowing virtualized network function (VNF) deployment at a low cost.
no code implementations • 17 Feb 2022 • DongNyeong Heo, Heeyoul Choi
Back-translation is an effective semi-supervised learning framework in neural machine translation (NMT).
no code implementations • 29 Sep 2021 • Chungjun Lee, Jibum Hong, DongNyeong Heo, Heeyoul Choi
Therefore, we propose several sequential deep learning models to learn time-series patterns and sequential patterns of the virtual network functions (VNFs) in the chain with variable lengths.
no code implementations • 19 Sep 2021 • Daniela N. Rim, DongNyeong Heo, Heeyoul Choi
In this work, we propose adversarial training with contrastive learning (ATCL) to adversarially train a language processing task using the benefits of contrastive learning.
no code implementations • 17 Nov 2020 • DongNyeong Heo, Doyoung Lee, Hee-Gon Kim, Suhyun Park, Heeyoul Choi
In the management of computer network systems, the service function chaining (SFC) modules play an important role by generating efficient paths for network traffic through physical servers with virtualized network functions (VNF).
no code implementations • 11 Sep 2020 • DongNyeong Heo, Stanislav Lange, Hee-Gon Kim, Heeyoul Choi
Moreover, the GNN based model can be applied to a new network topology without re-designing and re-training.