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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Characterizing users' interests accurately plays a significant role in aneffective recommender system. The sequential recommender system can learnpowerful hidden representations of users from successive user-item interactionsand dynamic users' preferences. To analyze such sequential data, conventionalmethods mainly include Markov Chains (MCs) and Recurrent Neural Networks(RNNs). Recently, the use of self-attention mechanisms and bi-directionalarchitectures have gained much attention. However, there still exists a majorlimitation in previous works that they only model the user's main purposes inthe behavioral sequences separately and locally, and they lack the globalrepresentation of the user's whole sequential behavior. To address thislimitation, we propose a novel bidirectional sequential recommendationalgorithm that integrates the user's local purposes with the global preferenceby additive supervision of the matching task. We combine the mask task with thematching task in the training process of the bidirectional encoder. A newsample production method is also introduced to alleviate the effect of masknoise. Our proposed model can not only learn bidirectional semantics fromusers' behavioral sequences but also explicitly produces user representationsto capture user's global preference. Extensive empirical studies demonstrateour approach considerably outperforms various state-of-the-art models.

Match4Rec: A Novel Recommendation Algorithm Based on Bidirectional Encoder Representation with the Matching Task