The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation

arXiv:2403.18031v1 Announce Type: new
Abstract: Unsupervised on-the-fly back-translation, in conjunction with multilingual pretraining, is the dominant method for unsupervised neural machine translation. Theoretically, however, the method should not work in general. We therefore conduct controlled experiments with artificial languages to determine what properties of languages make back-translation an effective training method, covering lexical, syntactic, and semantic properties. We find, contrary to popular belief, that (i) parallel word frequency distributions, (ii) partially shared vocabulary, and (iii) similar syntactic structure across languages …

abstract artificial arxiv cs.cl fly general however impact languages machine machine translation multilingual neural machine translation pretraining semantic translation type unsupervised work