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

Conversational Recommendation System (CRS) is a rapidly growing research areathat has gained significant attention alongside advancements in languagemodelling techniques. However, the current state of conversationalrecommendation faces numerous challenges due to its relative novelty andlimited existing contributions. In this study, we delve into benchmark datasetsfor developing CRS models and address potential biases arising from thefeedback loop inherent in multi-turn interactions, including selection bias andmultiple popularity bias variants. Drawing inspiration from the success ofgenerative data via using language models and data augmentation techniques, wepresent two novel strategies, 'Once-Aug' and 'PopNudge', to enhance modelperformance while mitigating biases. Through extensive experiments on ReDialand TG-ReDial benchmark datasets, we show a consistent improvement of CRStechniques with our data augmentation approaches and offer additional insightson addressing multiple newly formulated biases.

Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation