Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages. (arXiv:2308.05574v1 [cs.CL])

Current research in zero-shot translation is plagued by several issues such
as high compute requirements, increased training time and off target
translations. Proposed remedies often come at the cost of additional data or
compute requirements. Pivot based neural machine translation is preferred over
a single-encoder model for most settings despite the increased training and
evaluation time. In this work, we overcome the shortcomings of zero-shot
translation by taking advantage of transliteration and linguistic similarity.
We build a single encoder-decoder neural …

arxiv compute cost current data encoder languages machine machine translation multilingual neural machine translation pivot requirements research training translation