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

Most of ranking models are trained only with displayed items (most are hotitems), but they are utilized to retrieve items in the entire space whichconsists of both displayed and non-displayed items (most are long-tail items).Due to the sample selection bias, the long-tail items lack sufficient recordsto learn good feature representations, i.e. data sparsity and cold startproblems. The resultant distribution discrepancy between displayed andnon-displayed items would cause poor long-tail performance. To this end, wepropose an entire space adaptation model (ESAM) to address this problem fromthe perspective of domain adaptation (DA). ESAM regards displayed andnon-displayed items as source and target domains respectively. Specifically, wedesign the attribute correlation alignment that considers the correlationbetween high-level attributes of the item to achieve distribution alignment.Furthermore, we introduce two effective regularization strategies, i.e.\textit{center-wise clustering} and \textit{self-training} to improve DAprocess. Without requiring any auxiliary information and auxiliary domains,ESAM transfers the knowledge from displayed items to non-displayed items foralleviating the distribution inconsistency. Experiments on two public datasetsand a large-scale industrial dataset collected from Taobao demonstrate thatESAM achieves state-of-the-art performance, especially in the long-tail space.Besides, we deploy ESAM to the Taobao search engine, leading to significantimprovement on online performance. The code is available at\url{https://github.com/A-bone1/ESAM.git}

ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance