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 …
(NMT) models to become extremely powerful, given sufficient training data and training time …
Addressing domain shift in neural machine translation via reinforcement learning
Abstract Domain Adaptation (DA) has been a well-known transfer learning algorithm used in
Neural Machine Translation (NMT) task. Adding domain-related corpora in training data to …
Neural Machine Translation (NMT) task. Adding domain-related corpora in training data to …
T-STAR: Truthful style transfer using AMR graph as intermediate representation
Unavailability of parallel corpora for training text style transfer (TST) models is a very
challenging yet common scenario. Also, TST models implicitly need to preserve the content …
challenging yet common scenario. Also, TST models implicitly need to preserve the content …
Iterative constrained back-translation for unsupervised domain adaptation of machine translation
H Zhang, H Huang, J Gao, Y Chen… - Proceedings of the 29th …, 2022 - aclanthology.org
Back-translation has been proven to be effective in unsupervised domain adaptation of
neural machine translation (NMT). However, the existing back-translation methods mainly …
neural machine translation (NMT). However, the existing back-translation methods mainly …
Exploiting language relatedness in machine translation through domain adaptation techniques
One of the significant challenges of Machine Translation (MT) is the scarcity of large
amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as …
amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as …
The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation
N Guerin, S Steinert-Threlkeld, E Chemla - arXiv preprint arXiv …, 2024 - arxiv.org
Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the
dominant method for unsupervised neural machine translation. Theoretically, however, the …
dominant method for unsupervised neural machine translation. Theoretically, however, the …
基于词典注入的藏汉机器翻译模型预训练方法(Dictionary Injection Based Pretraining Method for Tibetan-Chinese Machine Translation Model)
D Sangjie, J Cairang - Proceedings of the 21st Chinese National …, 2022 - aclanthology.org
Abstract “近年来, 预训练方法在自然语言处理领域引起了广泛关注, 但是在比如藏汉机器等低
资源的任务设定下, 由于双语监督信息无法直接参与预训练, 限制了预训练模型在此类任务上的 …
资源的任务设定下, 由于双语监督信息无法直接参与预训练, 限制了预训练模型在此类任务上的 …
Finding the right recipe for low resource domain adaptation in neural machine translation
General translation models often still struggle to generate accurate translations in
specialized domains. To guide machine translation practitioners and characterize the …
specialized domains. To guide machine translation practitioners and characterize the …
Zero-Shot Cross-Lingual Domain Adaptation for Neural Machine Translation: Exploring The Interplay Between Language And Domain Transferability
L Shahnazaryan - 2024 - diva-portal.org
Within the field of neural machine translation (NMT), transfer learning and domain
adaptation techniques have emerged as central solutions to overcome the data scarcity …
adaptation techniques have emerged as central solutions to overcome the data scarcity …
[PDF][PDF] Towards Effective Ranking In Machine Translation Systems
V Pandramish - 2022 - cdn.iiit.ac.in
Abstract Machine Translation is an area of Natural Language Processing that involves
building systems that translate information from one language to another. Over the past few …
building systems that translate information from one language to another. Over the past few …