The field of machine translation (MT), the automatic translation of written text from one
natural language into another, has experienced a major paradigm shift in recent years …

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 …

While back-translation is simple and effective in exploiting abundant monolingual corpora to
improve low-resource neural machine translation (NMT), the synthetic bilingual corpora …

Low-resource languages (LRL) with complex morphology are known to be more difficult to
translate in an automatic way. Some LRLs are particularly more difficult to translate than …

Large-scale morphological databases provide essential input to a wide range of NLP
applications. Inflectional data is of particular importance for morphologically rich …

Tokenization or segmentation is a wide concept that covers simple processes such as
separating punctuation from words, or more sophisticated processes such as applying …

We report the findings of the second edition of the shared task on improving robustness in
Machine Translation (MT). The task aims to test current machine translation systems in their …

Abstract Byte-Pair Encoding (BPE) is an unsupervised sub-word tokenization technique,
commonly used in neural machine translation and other NLP tasks. Its effectiveness makes it …

Neural machine translation (NMT) models are typically trained with fixed-size input and
output vocabularies, which creates an important bottleneck on their accuracy and …

Neural machine translation (NMT) models are conventionally trained with fixed-size
vocabularies to control the computational complexity and the quality of the learned word …