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

Recommendation systems aim to assist users to discover most preferredcontents from an ever-growing corpus of items. Although recommenders have beengreatly improved by deep learning, they still faces several challenges: (1)Behaviors are much more complex than words in sentences, so traditionalattentive and recurrent models may fail in capturing the temporal dynamics ofuser preferences. (2) The preferences of users are multiple and evolving, so itis difficult to integrate long-term memory and short-term intent.  In this paper, we propose a temporal gating methodology to improve attentionmechanism and recurrent units, so that temporal information can be consideredin both information filtering and state transition. Additionally, we propose aMulti-hop Time-aware Attentive Memory network (MTAM) to integrate long-term andshort-term preferences. We use the proposed time-aware GRU network to learn theshort-term intent and maintain prior records in user memory. We treat theshort-term intent as a query and design a multi-hop memory reading operationvia the proposed time-aware attention to generate user representation based onthe current intent and long-term memory. Our approach is scalable for candidateretrieval tasks and can be viewed as a non-linear generalization of latentfactorization for dot-product based Top-K recommendation. Finally, we conductextensive experiments on six benchmark datasets and the experimental resultsdemonstrate the effectiveness of our MTAM and temporal gating methodology.

Sequential Recommender via Time-aware Attentive Memory Network