Consistency regularization methods, such as R-Drop (Liang et al., 2021) ...
Multilingual sentence representations are the foundation for similarity-...
The multilingual neural machine translation (NMT) model has a promising
...
We introduce Bi-SimCut: a simple but effective training strategy to boos...
Diverse machine translation aims at generating various target language
t...
This paper presents BSTC (Baidu Speech Translation Corpus), a large-scal...
Speech-to-text translation (ST), which translates source language speech...
Conventional Neural Machine Translation (NMT) models benefit from the
tr...
In this paper, we present DuTongChuan, a novel context-aware translation...
End-to-end speech translation (ST), which directly translates from sourc...
Discourse coherence plays an important role in the translation of one te...
Simultaneous translation, which translates sentences before they are
fin...
Neural machine translation (NMT) is notoriously sensitive to noises, but...
Attention-based Encoder-Decoder has the effective architecture for neura...
While end-to-end neural machine translation (NMT) has made remarkable
pr...
The attentional mechanism has proven to be effective in improving end-to...
We propose minimum risk training for end-to-end neural machine translati...