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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multilingual neural machine translation aims at learning a single translationmodel for multiple languages. These jointly trained models often suffer fromperformance degradation on rich-resource language pairs. We attribute thisdegeneration to parameter interference. In this paper, we propose LaSS tojointly train a single unified multilingual MT model. LaSS learns LanguageSpecific Sub-network (LaSS) for each language pair to counter parameterinterference. Comprehensive experiments on IWSLT and WMT datasets with variousTransformer architectures show that LaSS obtains gains on 36 language pairs byup to 1.2 BLEU. Besides, LaSS shows its strong generalization performance ateasy extension to new language pairs and zero-shot translation.LaSS boostszero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codesand trained models are available at https://github.com/NLP-Playground/LaSS.

Learning Language Specific Sub-network for Multilingual Machine Translation