Dynamic context-guided capsule network for multimodal machine translation
Multimodal machine translation (MMT), which mainly focuses on enhancing text-only
translation with visual features, has attracted considerable attention from both computer …
translation with visual features, has attracted considerable attention from both computer …
Revisiting multi-domain machine translation
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 …
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
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 …
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 …
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
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 …
its original content without using parallel training data. In current dominant approaches …
End-to-end neural event coreference resolution
Conventional event coreference systems commonly use a pipeline architecture and rely
heavily on handcrafted features, which often causes error propagation problems and leads …
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
Many multi-domain neural machine translation (NMT) models achieve knowledge transfer
by enforcing one encoder to learn shared embedding across domains. However, this design …
by enforcing one encoder to learn shared embedding across domains. However, this design …
Towards user-driven neural machine translation
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 …
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
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 …
domain discrimination and translation has been widely considered in the Multi-Domain …
Data augmentation for low‐resource languages NMT guided by constrained sampling
Data augmentation (DA) is a ubiquitous approach for several text generation tasks.
Intuitively, in the machine translation paradigm, especially in low‐resource languages …
Intuitively, in the machine translation paradigm, especially in low‐resource languages …