M2M 100
material
ID: m2m100
Related Papers
Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
AbstractPrevious work mainly focuses on improving cross-lingual transfer for NLU tasks with a multilingual pretrained encoder (MPE), or improving the performance on supervised machine translation with BERT. However, it is …...
DENTRA: Denoising and Translation Pre-training for Multilingual Machine Translation
AbstractIn this paper, we describe our submission to the WMT-2022: Large-Scale Machine Translation Evaluation for African Languages under the Constrained Translation track. We introduce DENTRA, a novel pre-training strategy for …...
Teaching Unseen Low-resource Languages to Large Translation Models
AbstractIn recent years, large multilingual pre-trained neural machine translation model research has grown and it is common for these models to be publicly available for usage and fine-tuning. Low-resource languages …...