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 a novel architecture for explainable modeling of task-orienteddialogues with discrete latent variables to represent dialogue actions. Ourmodel is based on variational recurrent neural networks (VRNN) and requires noexplicit annotation of semantic information. Unlike previous works, ourapproach models the system and user turns separately and performs databasequery modeling, which makes the model applicable to task-oriented dialogueswhile producing easily interpretable action latent variables. We show that ourmodel outperforms previous approaches with less supervision in terms ofperplexity and BLEU on three datasets, and we propose a way to measure dialoguesuccess without the need for expert annotation. Finally, we propose a novel wayto explain semantics of the latent variables with respect to system actions.

Learning Interpretable Latent Dialogue Actions With Less Supervision