OPUS-CAT: Desktop NMT with CAT integration and local fine-tuning

Abstract

OPUS-CAT is a collection of software which enables translators to use neural machine translation in computer-assisted translation tools without exposing themselves to security and confidentiality risks inherent in online machine translation. OPUS-CAT uses the public OPUS-MT machine translation models, which are available for over a thousand language pairs. The generic OPUS-MT models can be fine-tuned with OPUS-CAT on the desktop using data for a specific client or domain.