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

Recommender systems trained on offline historical user behaviors areembracing conversational techniques to online query user preference. Unlikeprior conversational recommendation approaches that systemically combineconversational and recommender parts through a reinforcement learningframework, we propose CORE, a new offline-training and online-checking paradigmthat bridges a COnversational agent and REcommender systems via a unifieduncertainty minimization framework. It can benefit any recommendation platformin a plug-and-play style. Here, CORE treats a recommender system as an offlinerelevance score estimator to produce an estimated relevance score for eachitem; while a conversational agent is regarded as an online relevance scorechecker to check these estimated scores in each session. We define uncertaintyas the summation of unchecked relevance scores. In this regard, theconversational agent acts to minimize uncertainty via querying eitherattributes or items. Based on the uncertainty minimization framework, we derivethe expected certainty gain of querying each attribute and item, and develop anovel online decision tree algorithm to decide what to query at each turn.Experimental results on 8 industrial datasets show that CORE could beseamlessly employed on 9 popular recommendation approaches. We furtherdemonstrate that our conversational agent could communicate as a human ifempowered by a pre-trained large language model.

Lending Interaction Wings to Recommender Systems with Conversational Agents