no code implementations • ACL (WAT) 2021 • Hwichan Kim, Mamoru Komachi
In this paper, we introduce our TMU Neural Machine Translation (NMT) system submitted for the Patent task (Korean Japanese and English Japanese) of 8th Workshop on Asian Translation (Nakazawa et al., 2021).
no code implementations • AACL (WAT) 2020 • Hwichan Kim, Tosho Hirasawa, Mamoru Komachi
In this paper, we describe our TMU neural machine translation (NMT) system submitted for the Patent task (Korean→Japanese) of the 7th Workshop on Asian Translation (WAT 2020, Nakazawa et al., 2020).
no code implementations • 22 Mar 2024 • Hwichan Kim, Shota Sasaki, Sho Hoshino, Ukyo Honda
To confirm this hypothesis, we devise a method named Conditionally Parameterized LoRA (CondLoRA) that updates initial weight matrices with low-rank matrices derived from a single linear layer.
no code implementations • LREC 2022 • Hwichan Kim, Sangwhan Moon, Naoaki Okazaki, Mamoru Komachi
Training a model using North Korean data is the most straightforward approach to solving this problem, but there is insufficient data to train NMT models.
no code implementations • ACL 2020 • Hwichan Kim, Tosho Hirasawa, Mamoru Komachi
The primary limitation of North Korean to English translation is the lack of a parallel corpus; therefore, high translation accuracy cannot be achieved.