This paper presents the results of the premier shared task organized alongside the
Conference on Machine Translation (WMT) 2019. Participants were asked to build machine …

We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

We explore the application of very deep Transformer models for Neural Machine Translation
(NMT). Using a simple yet effective initialization technique that stabilizes training, we show …

In this paper, we describe the submission of Tohoku-AIP-NTT to the WMT'20 news
translation task. We participated in this task in two language pairs and four language …

Back-translation is a data augmentation technique that has been shown to improve model
quality through the creation of synthetic training bitext. Early studies showed the promise of …

We conduct a large-scale fine-grained comparative analysis of machine translations (MTs)
against human translations (HTs) through the lens of morphosyntactic divergence. Across …

Reliably evaluating Machine Translation (MT) through automated metrics is a long-standing
problem. One of the main challenges is the fact that multiple outputs can be equally valid …

Machine translation (MT) is a maj or natural language processing subfield that is designed
to automatically translate human spoken languages. Neural machine translation (NMT) has …

Machine translation (MT) models used in industries with constantly changing topics, such as
translation or news agencies, need to adapt to new data to maintain their performance over …

Back-translation (BT) of target monolingual corpora is a widely used data augmentation
strategy for neural machine translation (NMT), especially for low-resource language pairs …