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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In learning-to-rank (LTR), optimizing only the relevance (or the expectedranking utility) can cause representational harm to certain categories ofitems. Moreover, if there is implicit bias in the relevance scores, LTR modelsmay fail to optimize for true relevance. Previous works have proposed efficientalgorithms to train stochastic ranking models that achieve fairness of exposureto the groups ex-ante (or, in expectation), which may not guaranteerepresentation fairness to the groups ex-post, that is, after realizing aranking from the stochastic ranking model. Typically, ex-post fairness isachieved by post-processing, but previous work does not train stochasticranking models that are aware of this post-processing.  In this paper, we propose a novel objective that maximizes expected relevanceonly over those rankings that satisfy given representation constraints toensure ex-post fairness. Building upon recent work on an efficient sampler forex-post group-fair rankings, we propose a group-fair Plackett-Luce model andshow that it can be efficiently optimized for our objective in the LTRframework.  Experiments on three real-world datasets show that our group-fair algorithmguarantees fairness alongside usually having better relevance compared to theLTR baselines. In addition, our algorithm also achieves better relevance thanpost-processing baselines, which also ensures ex-post fairness. Further, whenimplicit bias is injected into the training data, our algorithm typicallyoutperforms existing LTR baselines in relevance.

Optimizing Group-Fair Plackett-Luce Ranking Models for Relevance and Ex-Post Fairness