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

Multi-scenario & multi-task learning has been widely applied to manyrecommendation systems in industrial applications, wherein an effective andpractical approach is to carry out multi-scenario transfer learning on thebasis of the Mixture-of-Expert (MoE) architecture. However, the MoE-basedmethod, which aims to project all information in the same feature space, cannoteffectively deal with the complex relationships inherent among variousscenarios and tasks, resulting in unsatisfactory performance. To tackle theproblem, we propose a Hierarchical information extraction Network (HiNet) formulti-scenario and multi-task recommendation, which achieves hierarchicalextraction based on coarse-to-fine knowledge transfer scheme. The multipleextraction layers of the hierarchical network enable the model to enhance thecapability of transferring valuable information across scenarios whilepreserving specific features of scenarios and tasks. Furthermore, a novelscenario-aware attentive network module is proposed to model correlationsbetween scenarios explicitly. Comprehensive experiments conducted on real-worldindustrial datasets from Meituan Meishi platform demonstrate that HiNetachieves a new state-of-the-art performance and significantly outperformsexisting solutions. HiNet is currently fully deployed in two scenarios and hasachieved 2.87% and 1.75% order quantity gain respectively.

HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction