Наборы данных для перевода
Related Papers
Expected Sequence Similarity Maximization
This paper presents efficient algorithms for expected similarity maximization, which co- incides with minimum Bayes decoding for a similarity-based loss function. Our algorithms are designed for similarity functions that are …...
ReWE: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems
AbstractRegularization of neural machine translation is still a significant problem, especially in low-resource settings. To mollify this problem, we propose regressing word embeddings (ReWE) as a new regularization technique in …...
Touch Editing: A Flexible One-Time Interaction Approach for Translation
AbstractWe propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting. This approach relies on touch actions that users perform to indicate translation errors. …...
Improving Non-Autoregressive Neural Machine Translation via Modeling Localness
AbstractNon-autoregressive translation (NAT) models, which eliminate the sequential dependencies within the target sentence, have achieved remarkable inference speed, but suffer from inferior translation quality. Towards exploring the underlying causes, we …...
Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model
AbstractThis paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked …...