Sub-word segmentation is an essential pre-processing step for Neural Mac...
Discriminative pre-trained language models (PLMs) learn to predict origi...
Multilingual pretrained models are effective for machine translation and...
Conversational machine reading (CMR) requires machines to communicate wi...
In this paper we present our open-source neural machine translation (NMT...
Morphological analysis (MA) and lexical normalization (LN) are both impo...
Text encoding is one of the most important steps in Natural Language
Pro...
In this paper, we introduced our joint team SJTU-NICT 's participation i...
The global pandemic of COVID-19 has made the public pay close attention ...
Unsupervised neural machine translation (UNMT) has recently achieved
rem...
Unsupervised neural machine translation (UNMT) that relies solely on mas...
In Transformer-based neural machine translation (NMT), the positional
en...
Exploiting common language as an auxiliary for better translation has a ...
Existing neural machine translation (NMT) systems utilize
sequence-to-se...
Unsupervised neural machine translation (UNMT) has recently attracted gr...
Sequence-to-sequence (S2S) pre-training using large monolingual data is ...
State-of-the-art Transformer-based neural machine translation (NMT) syst...
We present a universal framework to model contextualized sentence
repres...
Standard neural machine translation (NMT) is on the assumption of
docume...
Reduction of training time is an important issue in many tasks like pate...
Domain adaptation methods have been well-studied in supervised neural ma...
This paper presents the NICT's participation in the WMT18 shared paralle...
This paper presents the NICT's participation to the WMT18 shared news
tr...
In Neural Machine Translation (NMT), the decoder can capture the feature...
Traditional Neural machine translation (NMT) involves a fixed training
p...
This paper presented an open-source neural machine translation toolkit n...
Attention mechanism, including global attention and local attention, pla...
The attention mechanisim is appealing for neural machine translation, si...
Most of the existing methods for bilingual word embedding only consider
...