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

Human knowledge is collectively encoded in the roughly 6500 languages spokenaround the world, but it is not distributed equally across languages. Hence,for information-seeking question answering (QA) systems to adequately servespeakers of all languages, they need to operate cross-lingually. In this workwe investigate the capabilities of multilingually pre-trained language modelson cross-lingual QA. We find that explicitly aligning the representationsacross languages with a post-hoc fine-tuning step generally leads to improvedperformance. We additionally investigate the effect of data size as well as thelanguage choice in this fine-tuning step, also releasing a dataset forevaluating cross-lingual QA systems. Code and dataset are publicly availablehere: https://github.com/ffaisal93/aligned_qa

Investigating Post-pretraining Representation Alignment for Cross-Lingual Question Answering