Resolving semantic ambiguity has long been recognised as a central chall...
Multilingual machine translation (MMT), trained on a mixture of parallel...
Large-scale multilingual machine translation systems have demonstrated
r...
Research on prompting has shown excellent performance with little or eve...
Task-oriented dialogue (TOD) systems have been applied in a range of dom...
Automatic machine translation (MT) metrics are widely used to distinguis...
Back translation is one of the most widely used methods for improving th...
Theoretical work in morphological typology offers the possibility of
mea...
Efficient machine translation models are commercially important as they ...
Neural machine learning models can successfully model language that is
s...
Recent progress in task-oriented neural dialogue systems is largely focu...
Large-Scale Multi-Label Text Classification (LMTC) includes tasks with
h...
We present a survey covering the state of the art in low-resource machin...
Unsupervised cross-lingual pretraining has achieved strong results in ne...
Machine translation (MT) models used in industries with constantly chang...
The scarcity of large parallel corpora is an important obstacle for neur...
Sparse language vectors from linguistic typology databases and learned
e...
Document-level machine translation manages to outperform sentence level
...
Translation into morphologically-rich languages challenges neural machin...
This document describes the findings of the Third Workshop on Neural
Gen...
Neural Machine Translation (NMT) models generally perform translation us...
The University of Edinburgh participated in the WMT19 Shared Task on New...
A popular application of machine translation (MT) is gisting: MT is cons...
This document describes the findings of the Second Workshop on Neural Ma...
We present Marian, an efficient and self-contained Neural Machine Transl...
For machine translation to tackle discourse phenomena, models must have
...
This paper describes the University of Edinburgh's submissions to the WM...
It has been shown that increasing model depth improves the quality of ne...
We present Nematus, a toolkit for Neural Machine Translation. The toolki...
Neural machine translation (NMT) models are able to partially learn synt...
Human evaluation of machine translation normally uses sentence-level mea...
We participated in the WMT 2016 shared news translation task by building...
Neural Machine Translation (NMT) has obtained state-of-the art performan...
Neural machine translation (NMT) models typically operate with a fixed
v...