Customer feedback can be an important signal for improving commercial ma...
A major open problem in neural machine translation (NMT) is the translat...
Vocabulary selection, or lexical shortlisting, is a well-known technique...
Despite the impressive quality improvements yielded by neural machine
tr...
We describe a batched beam decoding algorithm for NMT with LMBR n-gram
p...
We compare several language models for the word-ordering task and propos...
This paper introduces SGNMT, our experimental platform for machine
trans...
We present a novel scheme to combine neural machine translation (NMT) wi...
This paper presents the University of Cambridge submission to WMT16.
Mot...
We investigate the use of hierarchical phrase-based SMT lattices in
end-...
In this paper we present an approach to multi-language image description...