English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multilingual neural machine translation models (MNMT) yield state-of-the-artperformance when evaluated on data from a domain and language pair seen attraining time. However, when a MNMT model is used to translate under domainshift or to a new language pair, performance drops dramatically. We consider avery challenging scenario: adapting the MNMT model both to a new domain and toa new language pair at the same time. In this paper, we propose $m^4Adapter$(Multilingual Multi-Domain Adaptation for Machine Translation with aMeta-Adapter), which combines domain and language knowledge using meta-learningwith adapters. We present results showing that our approach is aparameter-efficient solution which effectively adapts a model to both a newlanguage pair and a new domain, while outperforming other adapter methods. Anablation study also shows that our approach more effectively transfers domainknowledge across different languages and language information across differentdomains.

$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter