US Patent Issued to NAVER on April 21 for "Multimodal text-to-text neural machine translation using noise and domain adapters and training noise adapters while a domain adapter is frozen" (Japanese, French Inventors)

ALEXANDRIA, Va., April 21 -- United States Patent no. 12,608,565, issued on April 21, was assigned to NAVER Corp. (Seongnam-si, South Korea).

"Multimodal text-to-text neural machine translation using noise and domain adapters and training noise adapters while a domain adapter is frozen" was invented by Ioan Calapodescu (Grenoble, France) and Yuting Zhao (Fukuoka, Japan).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems for adapting a pretrained neural machine translation (NMT) model for translating text from a noisy input in a domain. A domain adapter injected into the pretrained NMT model is trained on clean in-domain data for adapting the pretrained NMT to the domain. Each of a plurality of...