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

Learning-to-rank is a core technique in the top-N recommendation task, wherean ideal ranker would be a mapping from an item set to an arrangement (a.k.a.permutation). Most existing solutions fall in the paradigm of probabilisticranking principle (PRP), i.e., first score each item in the candidate set andthen perform a sort operation to generate the top ranking list. However, theseapproaches neglect the contextual dependence among candidate items duringindividual scoring, and the sort operation is non-differentiable. To bypass theabove issues, we propose Set-To-Arrangement Ranking (STARank), a new frameworkdirectly generates the permutations of the candidate items without the need forindividually scoring and sort operations; and is end-to-end differentiable. Asa result, STARank can operate when only the ground-truth permutations areaccessible without requiring access to the ground-truth relevance scores foritems. For this purpose, STARank first reads the candidate items in the contextof the user browsing history, whose representations are fed into aPlackett-Luce module to arrange the given items into a list. To effectivelyutilize the given ground-truth permutations for supervising STARank, weleverage the internal consistency property of Plackett-Luce models to derive acomputationally efficient list-wise loss. Experimental comparisons against 9the state-of-the-art methods on 2 learning-to-rank benchmark datasets and 3top-N real-world recommendation datasets demonstrate the superiority of STARankin terms of conventional ranking metrics. Notice that these ranking metrics donot consider the effects of the contextual dependence among the items in thelist, we design a new family of simulation-based ranking metrics, whereexisting metrics can be regarded as special cases. STARank can consistentlyachieve better performance in terms of PBM and UBM simulation-based metrics.

Replace Scoring with Arrangement: A Contextual Set-to-Arrangement Framework for Learning-to-Rank