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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Task-oriented dialogue (TOD) systems have been widely deployed in manyindustries as they deliver more efficient customer support. These systems aretypically constructed for a single domain or language and do not generalisewell beyond this. To support work on Natural Language Understanding (NLU) inTOD across multiple languages and domains simultaneously, we constructedMULTI3NLU++, a multilingual, multi-intent, multi-domain dataset. MULTI3NLU++extends the English only NLU++ dataset to include manual translations into arange of high, medium, and low resource languages (Spanish, Marathi, Turkishand Amharic), in two domains (BANKING and HOTELS). Because of its multi-intentproperty, MULTI3NLU++ represents complex and natural user goals, and thereforeallows us to measure the realistic performance of TOD systems in a varied setof the world's languages. We use MULTI3NLU++ to benchmark state-of-the-artmultilingual models for the NLU tasks of intent detection and slot labellingfor TOD systems in the multilingual setting. The results demonstrate thechallenging nature of the dataset, particularly in the low-resource languagesetting, offering ample room for future experimentation in multi-domainmultilingual TOD setups.

MULTI3NLU++: A Multilingual, Multi-Intent, Multi-Domain Dataset for Natural Language Understanding in Task-Oriented Dialogue