← Search

Hantae Kim

2 accepted papers

2022

DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation

ACL 2022findings

Domain Adaptation (DA) of Neural Machine Translation (NMT) model often relies on a pre-trained general NMT model which is adapted to the new domain on a sample of in-domain parallel data. Without parallel data, there is no way to estimate the potential benefit of DA, nor the amount of parallel sampl…

2022

Specializing Multi-domain NMT via Penalizing Low Mutual Information

EMNLP 2022main

Multi-domain Neural Machine Translation (NMT) trains a single model with multiple domains. It is appealing because of its efficacy in handling multiple domains within one model. An ideal multi-domain NMT learns distinctive domain characteristics simultaneously, however, grasping the domain peculiari…