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

Recent studies have demonstrated promising outcomes by employing largelanguage models with multi-tasking capabilities. They utilize prompts to guidethe model's behavior and surpass performance of task-specific models. Motivatedby this, we ask: can we build a single model that jointly perform variousspoken language understanding (SLU) tasks? To address this, we utilizepre-trained automatic speech recognition (ASR) models and employ various taskand dataset specifiers as discrete prompts. We demonstrate efficacy of oursingle multi-task learning (MTL) model "UniverSLU" for 12 different speechclassification and sequence generation tasks across 17 datasets and 9languages. Results show that UniverSLU achieves competitive performance andeven surpasses task-specific models. We also conduct preliminary investigationsinto enabling human-interpretable natural phrases instead of task specifiers asdiscrete prompts and test the model's generalization capabilities to newparaphrases.

UniverSLU: Universal Spoken Language Understanding for Diverse Classification and Sequence Generation Tasks with a Single Network