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

In Conversational Recommendation Systems (CRS), a user can provide feedbackon recommended items at each interaction turn, leading the CRS towards moredesirable recommendations. Currently, different types of CRS offer variouspossibilities for feedback, i.e., natural language feedback, or answeringclarifying questions. In most cases, a user simulator is employed for trainingas well as evaluating the CRS. Such user simulators typically critique thecurrent retrieved items based on knowledge of a single target item. Still,evaluating systems in offline settings with simulators suffers from problems,such as focusing entirely on a single target item (not addressing theexploratory nature of a recommender system), and exhibiting extreme patience(consistent feedback over a large number of turns). To overcome theselimitations, we obtain extra judgements for a selection of alternative items incommon CRS datasets, namely Shoes and Fashion IQ Dresses. Going further, wepropose improved user simulators that allow simulated users not only to expresstheir preferences about alternative items to their original target, but also tochange their mind and level of patience. In our experiments using the relativeimage captioning CRS setting and different CRS models, we find that using theknowledge of alternatives by the simulator can have a considerable impact onthe evaluation of existing CRS models, specifically that the existingsingle-target evaluation underestimates their effectiveness, and when simulatedusers are allowed to instead consider alternatives, the system can rapidlyrespond to more quickly satisfy the user.

What Else Would I Like? A User Simulator using Alternatives for Improved Evaluation of Fashion Conversational Recommendation Systems