Ключевое слово: «unsupervised learning.»

Machine Translation (MT) has evolved from rigid rule-based systems to statistical methods and finally to neural architectures. While Supervised Neural Machine Translation (NMT) achieves high performance, it depends heavily on large parallel corpora. This survey reviews the techni- cal evolution of MT state-of-the-art (SOTA) approaches and analyzes Unsupervised Machine Translation (UMT). We examine how modern models learn translation mappings using only monolingual data, de- coupling performance from the availability of bilingual datasets.