Dynamic context-guided capsule network for multimodal machine translation

H Lin, F Meng, J Su, Y Yin, Z Yang, Y Ge… - Proceedings of the 28th …, 2020‏ - dl.acm.org
Multimodal machine translation (MMT), which mainly focuses on enhancing text-only
translation with visual features, has attracted considerable attention from both computer …

Revisiting multi-domain machine translation

MQ Pham, JM Crego, F Yvon - Transactions of the Association for …, 2021‏ - direct.mit.edu
When building machine translation systems, one often needs to make the best out of
heterogeneous sets of parallel data in training, and to robustly handle inputs from …

Enriching the transfer learning with pre-trained lexicon embedding for low-resource neural machine translation

M Maimaiti, Y Liu, H Luan, M Sun - Tsinghua Science and …, 2021‏ - ieeexplore.ieee.org
Most State-Of-The-Art (SOTA) Neural Machine Translation (NMT) systems today achieve
outstanding results based only on large parallel corpora. The large-scale parallel corpora for …

Enhancing low-resource neural machine translation with syntax-graph guided self-attention

L Gong, Y Li, J Guo, Z Yu, S Gao - Knowledge-based systems, 2022‏ - Elsevier
Most neural machine translation (NMT) models only rely on parallel sentence pairs, while
the performance drops sharply in low-resource cases, as the models fail to mine the …

Exploring contextual word-level style relevance for unsupervised style transfer

C Zhou, L Chen, J Liu, X **ao, J Su, S Guo… - arxiv preprint arxiv …, 2020‏ - arxiv.org
Unsupervised style transfer aims to change the style of an input sentence while preserving
its original content without using parallel training data. In current dominant approaches …

End-to-end neural event coreference resolution

Y Lu, H Lin, J Tang, X Han, L Sun - Artificial Intelligence, 2022‏ - Elsevier
Conventional event coreference systems commonly use a pipeline architecture and rely
heavily on handcrafted features, which often causes error propagation problems and leads …

Multi-domain neural machine translation with word-level adaptive layer-wise domain mixing

H Jiang, C Liang, C Wang, T Zhao - arxiv preprint arxiv:1911.02692, 2019‏ - arxiv.org
Many multi-domain neural machine translation (NMT) models achieve knowledge transfer
by enforcing one encoder to learn shared embedding across domains. However, this design …

Towards user-driven neural machine translation

H Lin, L Yao, B Yang, D Liu, H Zhang, W Luo… - arxiv preprint arxiv …, 2021‏ - arxiv.org
A good translation should not only translate the original content semantically, but also
incarnate personal traits of the original text. For a real-world neural machine translation …

WDSRL: Multi-domain neural machine translation with word-level domain-sensitive representation learning

Z Man, Z Huang, Y Zhang, Y Li, Y Chen… - … on Audio, Speech …, 2023‏ - ieeexplore.ieee.org
Due to the strong reliance on domain-specific knowledge, the joint learning manner of
domain discrimination and translation has been widely considered in the Multi-Domain …

Data augmentation for low‐resource languages NMT guided by constrained sampling

M Maimaiti, Y Liu, H Luan, M Sun - International Journal of …, 2022‏ - Wiley Online Library
Data augmentation (DA) is a ubiquitous approach for several text generation tasks.
Intuitively, in the machine translation paradigm, especially in low‐resource languages …