Feb. 28, 2024, 5:44 a.m. | Di Wu, Shaomu Tan, Yan Meng, David Stap, Christof Monz

cs.LG updates on arXiv.org arxiv.org

arXiv:2401.12413v2 Announce Type: replace-cross
Abstract: Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem. A common, albeit resource-consuming, solution is to add as many related translation directions as possible to the training corpus. In this paper, we show that for an English-centric model, surprisingly large zero-shot improvements can be achieved by simply fine-tuning with a very small amount of multi-parallel data. For example, on the …

abstract arxiv cs.cl cs.lg data language machine machine translation multilingual samples solution training translate translation type via zero-shot

Data Scientist (m/f/x/d)

@ Symanto Research GmbH & Co. KG | Spain, Germany

Aumni - Site Reliability Engineer III - MLOPS

@ JPMorgan Chase & Co. | Salt Lake City, UT, United States

Senior Data Analyst

@ Teya | Budapest, Hungary

Technical Analyst (Data Analytics)

@ Contact Government Services | Chicago, IL

Engineer, AI/Machine Learning

@ Masimo | Irvine, CA, United States

Private Bank - Executive Director: Data Science and Client / Business Intelligence

@ JPMorgan Chase & Co. | Mumbai, Maharashtra, India