Journal article
Yunwon Tae, Cheonbok Park, Taehee Kim, Soyoung Yang, Mohammad Azam Khan, Eunjeong Park, Tao Qin, J. Choo
arXiv.org, 2020
arXiv.org, 2020
Semantic Scholar
DBLP
Cite
Cite
APA
Click to copy
Tae, Y., Park, C., Kim, T., Yang, S., Khan, M. A., Park, E., … Choo, J. (2020). Meta-Learning for Low-Resource Unsupervised Neural MachineTranslation. ArXiv.org.
Chicago/Turabian
Click to copy
Tae, Yunwon, Cheonbok Park, Taehee Kim, Soyoung Yang, Mohammad Azam Khan, Eunjeong Park, Tao Qin, and J. Choo. “Meta-Learning for Low-Resource Unsupervised Neural MachineTranslation.” arXiv.org (2020).
MLA
Click to copy
Tae, Yunwon, et al. “Meta-Learning for Low-Resource Unsupervised Neural MachineTranslation.” ArXiv.org, 2020.
BibTeX Click to copy
@article{yunwon2020a,
title = {Meta-Learning for Low-Resource Unsupervised Neural MachineTranslation},
year = {2020},
journal = {arXiv.org},
author = {Tae, Yunwon and Park, Cheonbok and Kim, Taehee and Yang, Soyoung and Khan, Mohammad Azam and Park, Eunjeong and Qin, Tao and Choo, J.}
}
Abstract
Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domains. To address this issue, this paper presents a meta-learning algorithm for unsupervised neural machine translation (UNMT) that trains the model to adapt to another domain by utilizing only a small amount of training data. We assume that domain-general knowledge is a significant factor in handling data-scarce domains. Hence, we extend the meta-learning algorithm, which utilizes knowledge learned from high-resource domains to boost the performance of low-resource UNMT. Our model surpasses a transfer learning-based approach by up to 2-4 BLEU scores. Extensive experimental results show that our proposed algorithm is pertinent for fast adaptation and consistently outperforms other baseline models.
