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

Adapters and Low-Rank Adaptation (LoRA) are parameter-efficient fine-tuningtechniques designed to make the training of language models more efficient.Previous results demonstrated that these methods can even improve performanceon some classification tasks. This paper complements the existing research byinvestigating how these techniques influence the classification performance andcomputation costs compared to full fine-tuning when applied to multilingualtext classification tasks (genre, framing, and persuasion techniques detection;with different input lengths, number of predicted classes and classificationdifficulty), some of which have limited training data. In addition, we conductin-depth analyses of their efficacy across different training scenarios(training on the original multilingual data; on the translations into English;and on a subset of English-only data) and different languages. Our findingsprovide valuable insights into the applicability of the parameter-efficientfine-tuning techniques, particularly to complex multilingual and multilabelclassification tasks.

Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification