Towards Faster k-Nearest-Neighbor Machine Translation
Recent works have proven the effectiveness of k-nearest-neighbor machine translation (aka
kNN-MT) approaches to produce remarkable improvement in cross-domain translations …
kNN-MT) approaches to produce remarkable improvement in cross-domain translations …
Domain-Aware k-Nearest-Neighbor Knowledge Distillation for Machine Translation
Abstract k NN-MT has utilized neighborhood knowledge for auxiliary decoding, significantly
improving translation performance. Subsequently, k NN-KD transitions the use of …
improving translation performance. Subsequently, k NN-KD transitions the use of …
Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
To achieve non-parametric NMT domain adaptation, $ k $-Nearest-Neighbor Machine
Translation ($ k $ NN-MT) constructs an external datastore to store domain-specific …
Translation ($ k $ NN-MT) constructs an external datastore to store domain-specific …
Exploiting Target Language Data for Neural Machine Translation Beyond Back Translation
A Reheman, Y Luo, J Ruan, C Zhang… - Findings of the …, 2024 - aclanthology.org
Abstract Neural Machine Translation (NMT) encounters challenges when translating in new
domains and low-resource languages. To address these issues, researchers have proposed …
domains and low-resource languages. To address these issues, researchers have proposed …
融合确定性因子及区域密度的k-最近邻机器翻译方法(A k-Nearest-Neighbor Machine Translation Method Combining Certainty Factor and Region Density)
Q Rui, S Xiangyu, M Zhibo, X Jinan… - Proceedings of the 23rd …, 2024 - aclanthology.org
Abstract “k-最近邻机器翻译(kNN-MT) 是近年来神经机器翻译领域的一个重要研究方向.
此类方法可以在不更新机器翻译模型的情况下提高翻译质量, 但训练数据中高低频单词的数量不 …
此类方法可以在不更新机器翻译模型的情况下提高翻译质量, 但训练数据中高低频单词的数量不 …
A multi-domain adaptive neural machine translation method based on domain data balancer
J Xu, Y Wen, S Huang, Z Yu - Intelligent Data Analysis, 2024 - journals.sagepub.com
Most methods for multi-domain adaptive neural machine translation (NMT) currently rely on
mixing data from multiple domains in a single model to achieve multi-domain translation …
mixing data from multiple domains in a single model to achieve multi-domain translation …
[PDF][PDF] Towards Faster k-Nearest-Neighbor Machine Translation. Advances in Artificial Intelligence and Machine Learning. 2024; 4 (1): 111
X Shi - Learning, 2024 - oajaiml.com
Recent works have proven the effectiveness of k-nearest-neighbor machine translation (aka
kNN-MT) approaches to produce remarkable improvement in cross-domain translations …
kNN-MT) approaches to produce remarkable improvement in cross-domain translations …