Low-Resource Neural Machine Translation
23 papers with code • 1 benchmarks • 5 datasets
Low-resource machine translation is the task of machine translation on a low-resource language where large data may not be available.
Latest papers with no code
Naive Regularizers for Low-Resource Neural Machine Translation
Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios.
Corpus Augmentation by Sentence Segmentation for Low-Resource Neural Machine Translation
Neural Machine Translation (NMT) has been proven to achieve impressive results.
Target Conditioned Sampling: Optimizing Data Selection for Multilingual Neural Machine Translation
To improve low-resource Neural Machine Translation (NMT) with multilingual corpora, training on the most related high-resource language only is often more effective than using all data available (Neubig and Hu, 2018).
Trivial Transfer Learning for Low-Resource Neural Machine Translation
We present a simple transfer learning method, where we first train a "parent" model for a high-resource language pair and then continue the training on a lowresource pair only by replacing the training corpus.
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
Adaptive Knowledge Sharing in Multi-Task Learning: Improving Low-Resource Neural Machine Translation
The routing network enables adaptive collaboration by dynamic sharing of blocks conditioned on the task at hand, input, and model state.
Unsupervised Source Hierarchies for Low-Resource Neural Machine Translation
Incorporating source syntactic information into neural machine translation (NMT) has recently proven successful (Eriguchi et al., 2016; Luong et al., 2016).
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.