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

While deep learning (DL) models are state-of-the-art in text and imagedomains, they have not yet consistently outperformed Gradient Boosted DecisionTrees (GBDTs) on tabular Learning-To-Rank (LTR) problems. Most of the recentperformance gains attained by DL models in text and image tasks have usedunsupervised pretraining, which exploits orders of magnitude more unlabeleddata than labeled data. To the best of our knowledge, unsupervised pretraininghas not been applied to the LTR problem, which often produces vast amounts ofunlabeled data.  In this work, we study whether unsupervised pretraining of deep models canimprove LTR performance over GBDTs and other non-pretrained models. Byincorporating simple design choices--including SimCLR-Rank, an LTR-specificpretraining loss--we produce pretrained deep learning models that consistently(across datasets) outperform GBDTs (and other non-pretrained rankers) in thecase where there is more unlabeled data than labeled data. This performanceimprovement occurs not only on average but also on outlier queries. We base ourempirical conclusions off of experiments on (1) public benchmark tabular LTRdatasets, and (2) a large industry-scale proprietary ranking dataset. Code isprovided at https://anonymous.4open.science/r/ltr-pretrain-0DAD/README.md.

Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity