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

Task-oriented dialogue (TOD) systems have been widely used by mobile phoneintelligent assistants to accomplish tasks such as calendar scheduling or hotelreservation. Current TOD systems usually focus on multi-turn text/speechinteraction, then they would call back-end APIs designed for TODs to performthe task. However, this API-based architecture greatly limits theinformation-searching capability of intelligent assistants and may even lead totask failure if TOD-specific APIs are not available or the task is toocomplicated to be executed by the provided APIs. In this paper, we propose anew TOD architecture: GUI-based task-oriented dialogue system (GUI-TOD). AGUI-TOD system can directly perform GUI operations on real APPs and executetasks without invoking TOD-specific backend APIs. Furthermore, we releaseMETA-GUI, a dataset for training a Multi-modal convErsaTional Agent on mobileGUI. We also propose a multi-model action prediction and response model, whichshow promising results on META-GUI. The dataset, codes and leaderboard arepublicly available.

META-GUI: Towards Multi-modal Conversational Agents on Mobile GUI