Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

arXiv:2404.02835v1 Announce Type: new
Abstract: Retrieval-Augmented Neural Machine Translation (RAMT) architectures retrieve examples from memory to guide the generation process. While most works in this trend explore new ways to exploit the retrieved examples, the upstream retrieval step is mostly unexplored. In this paper, we study the effect of varying retrieval methods for several translation architectures, to better understand the interplay between these two processes. We conduct experiments in two language pairs in a multi-domain setting and consider several downstream …

abstract architectures arxiv comparison cs.cl examples exploit explore guide machine machine translation memory neural machine translation paper process retrieval retrieval-augmented study translation trend type