Domain adaptation and multi-domain adaptation for neural machine translation: A survey

D Saunders - Journal of Artificial Intelligence Research, 2022 - jair.org
The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

Simple and scalable nearest neighbor machine translation

Y Dai, Z Zhang, Q Liu, Q Cui, W Li, Y Du… - arXiv preprint arXiv …, 2023 - arxiv.org
$ k $ NN-MT is a straightforward yet powerful approach for fast domain adaptation, which
directly plugs pre-trained neural machine translation (NMT) models with domain-specific …

Progressive modality-complement aggregative multitransformer for domain multi-modal neural machine translation

J Guo, Z Hou, Y Xian, Z Yu - Pattern Recognition, 2024 - Elsevier
Abstract Domain-specific Multi-modal Neural Machine Translation (DMNMT) aims to
translate domain-specific sentences from a source language to a target language by …

Dalc: Domain adaptation learning curve prediction for neural machine translation

C Park, H Kim, I Calapodescu, H Cho… - arXiv preprint arXiv …, 2022 - arxiv.org
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 …

Neural Machine Translation Transfer Model Based on Mutual Domain Guidance

Y Liu, L Zhang, Y Zhang - IEEE Access, 2022 - ieeexplore.ieee.org
The neural machine translation (NMT) model is a data hungry and domain-sensitive model
but it is almost impossible to obtain a large number of labeled data for training it. This …

Progressive Modality-Complement Aggregative Multitransformer for Domain Multi-Modal Machine Translation

J Guo, Z Hou, Y Xian, Z Yu - Available at SSRN 4560034 - papers.ssrn.com
Abstract Domain-specific Multi-modal Neural Machine Translation (DMNMT) aims to
translate domain-specific sentences from a source language to a target language by …