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

This paper proposes a simple yet effective method to improve direct (X-to-Y)translation for both cases: zero-shot and when direct data is available. Wemodify the input tokens at both the encoder and decoder to include signals forthe source and target languages. We show a performance gain when training fromscratch, or finetuning a pretrained model with the proposed setup. In theexperiments, our method shows nearly 10.0 BLEU points gain on in-house datasetsdepending on the checkpoint selection criteria. In a WMT evaluation campaign,From-English performance improves by 4.17 and 2.87 BLEU points, in thezero-shot setting, and when direct data is available for training,respectively. While X-to-Y improves by 1.29 BLEU over the zero-shot baseline,and 0.44 over the many-to-many baseline. In the low-resource setting, we see a1.5~1.7 point improvement when finetuning on X-to-Y domain data.

Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation