2 papers
cs.CL2024
Shared Latent Space by Both Languages in Non-Autoregressive Neural Machine Translation
DongNyeong Heo, Heeyoul Choi
Non-autoregressive neural machine translation (NAT) offers substantial translation speed up compared to autoregressive neural machine translation (AT) at the cost of translation qu…
cs.CL2024
End-to-End Training for Back-Translation with Categorical Reparameterization Trick
DongNyeong Heo, Heeyoul Choi
Back-translation (BT) is an effective semi-supervised learning framework in neural machine translation (NMT). A pre-trained NMT model translates monolingual sentences and makes syn…