WMT14 ағылшынша немісше
Related Papers
Deep Neural Machine Translation with Linear Associative Unit
AbstractDeep Neural Networks (DNNs) have provably enhanced the state-of-the-art Neural Machine Translation (NMT) with its capability in modeling complex functions and capturing complex linguistic structures. However NMT with deep architecture …...
Bridging the Gap between Training and Inference for Neural Machine Translation
AbstractNeural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth …...
Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation
AbstractMutual learning, where multiple agents learn collaboratively and teach one another, has been shown to be an effective way to distill knowledge for image classification tasks. In this paper, we …...
Multi-Unit Transformers for Neural Machine Translation
AbstractTransformer models achieve remarkable success in Neural Machine Translation. Many efforts have been devoted to deepening the Transformer by stacking several units (i.e., a combination of Multihead Attentions and FFN) …...
Train Once, and Decode As You Like
AbstractIn this paper we propose a unified approach for supporting different generation manners of machine translation, including autoregressive, semi-autoregressive, and refinement-based non-autoregressive models. Our approach works by repeatedly selecting positions …...
Memory-Efficient Differentiable Transformer Architecture Search
Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Trans- formers is memory-intensive, which renders the search process infeasible. To this end, we …...
Selective Knowledge Distillation for Neural Machine Translation
AbstractNeural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model’s performance by …...