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

Deep neural networks (DNNs) demonstrate significant advantages in improvingranking performance in retrieval tasks. Driven by the recent technicaldevelopments in optimization and generalization of DNNs, learning a neuralranking model online from its interactions with users becomes possible.However, the required exploration for model learning has to be performed in theentire neural network parameter space, which is prohibitively expensive andlimits the application of such online solutions in practice.  In this work, we propose an efficient exploration strategy for onlineinteractive neural ranker learning based on the idea of bootstrapping. Oursolution employs an ensemble of ranking models trained with perturbed userclick feedback. The proposed method eliminates explicit confidence setconstruction and the associated computational overhead, which enables theonline neural rankers' training to be efficiently executed in practice withtheoretical guarantees. Extensive comparisons with an array of state-of-the-artOL2R algorithms on two public learning to rank benchmark datasets demonstratethe effectiveness and computational efficiency of our proposed neural OL2Rsolution.

Scalable Exploration for Neural Online Learning to Rank with Perturbed Feedback