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

Zero-shot cross-lingual generation assumes finetuning the multilingualpretrained language model (mPLM) on a generation task in one language and thenusing it to make predictions for this task in other languages. Previous worksnotice a frequent problem of generation in a wrong language and proposeapproaches to address it, usually using mT5 as a backbone model. In this work,we test alternative mPLMs, such as mBART and NLLB-200, and compare variousapproaches proposed in the literature in a unified setting. We first underlinethe importance of tuning learning rate used for finetuning, which helps tosubstantially alleviate the problem of generation in the wrong language. Then,we show that with careful learning rate tuning, the simple full finetuning ofthe model acts as a very strong baseline; other competitive approaches includeparameter-efficient tuning with adapters and training on several sourcelanguages. Finally, we find that mBART performs similarly to mT5 of the samesize, and NLLB-200 can be competitive in some cases.

Empirical study of pretrained multilingual language models for zero-shot cross-lingual generation