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 models have inspired a new class of word alignmentmethods, which work well for the model's pretraining languages. However, thelanguages most in need of automatic alignment are low-resource and, thus, nottypically included in the pretraining data. In this work, we ask: How do modernaligners perform on unseen languages, and are they better than traditionalmethods? We contribute gold-standard alignments for Bribri--Spanish,Guarani--Spanish, Quechua--Spanish, and Shipibo-Konibo--Spanish. With these, weevaluate state-of-the-art aligners with and without model adaptation to thetarget language. Finally, we also evaluate the resulting alignmentsextrinsically through two downstream tasks: named entity recognition andpart-of-speech tagging. We find that although transformer-based methodsgenerally outperform traditional models, the two classes of approach remaincompetitive with each other.

Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models