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

Large multilingual pretrained language models such as mBERT and XLM-RoBERTahave been found to be surprisingly effective for cross-lingual transfer ofsyntactic parsing models (Wu and Dredze 2019), but only between relatedlanguages. However, source and training languages are rarely related, whenparsing truly low-resource languages. To close this gap, we adopt a method frommulti-task learning, which relies on automated curriculum learning, todynamically optimize for parsing performance on outlier languages. We show thatthis approach is significantly better than uniform and size-proportionalsampling in the zero-shot setting.

Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning