Machine translation systems achieve near human-level performance on some languages,
yet their effectiveness strongly relies on the availability of large amounts of parallel …

Recent work in NLP has attempted to deal with low-resource languages but still assumed a
resource level that is not present for most languages, eg, the availability of Wikipedia in the …

Neural Machine Translation (NMT) brings promising improvements in translation quality, but
until recently, these models rely on large-scale parallel corpora. As such corpora only exist …

The goal of this work is to design a machine translation (MT) system for a low-resource
family of dialects, collectively known as Swiss German, which are widely spoken in …

In this work, we propose a flow-adapter architecture for unsupervised NMT. It leverages
normalizing flows to explicitly model the distributions of sentence-level latent …

Purpose This paper aims to describe the structure of an aligned Serbian-German literary
corpus (SrpNemKor) contained in a digital library Bibliša. The goal of the research was to …

In this paper, we present two approaches and the implemented system for bilingual
terminology extraction that rely on an aligned bilingual domain corpus, a terminology …

Bilingual Lexicon Induction is the task of learning word translations without bilingual parallel
corpora. We model this task as a matrix completion problem, and present an effective and …

Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the
dominant method for unsupervised neural machine translation. Theoretically, however, the …

ABSTRACT Statistical Machine Translation (SMT) is making good progress in recent years.
Since SMT systems are based on data-driven approach, they learn from millions or even …