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

We present NLU++, a novel dataset for natural language understanding (NLU) intask-oriented dialogue (ToD) systems, with the aim to provide a much morechallenging evaluation environment for dialogue NLU models, up to date with thecurrent application and industry requirements. NLU++ is divided into twodomains (BANKING and HOTELS) and brings several crucial improvements overcurrent commonly used NLU datasets. 1) NLU++ provides fine-grained domainontologies with a large set of challenging multi-intent sentences, introducingand validating the idea of intent modules that can be combined into complexintents that convey complex user goals, combined with finer-grained and thusmore challenging slot sets. 2) The ontology is divided into domain-specific andgeneric (i.e., domain-universal) intent modules that overlap across domains,promoting cross-domain reusability of annotated examples. 3) The dataset designhas been inspired by the problems observed in industrial ToD systems, and 4) ithas been collected, filtered and carefully annotated by dialogue NLU experts,yielding high-quality annotated data. Finally, we benchmark a series of currentstate-of-the-art NLU models on NLU++; the results demonstrate the challengingnature of the dataset, especially in low-data regimes, the validity of `intentmodularisation', and call for further research on ToD NLU.

NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented Dialogue