RankFormer: Listwise Learning-to-Rank Using Listwide Labels
Maarten Buyl, Paul Missault, Pierre-Antoine Sondag
Abstract
Web applications where users are presented with a limited selection of items have long employed ranking models to put the most relevant results first. Any feedback received from users is typically assumed to reflect a relative judgement on the utility of items, e.g. a user clicking on an item only implies it is better than items not clicked in the same ranked list. Hence, the objectives optimized in Learning-to-Rank (LTR) tend to be pairwise or listwise.
Topics & Concepts
Computer scienceRank (graph theory)Learning to rankArtificial intelligenceMachine learningRanking (information retrieval)MathematicsCombinatoricsText and Document Classification TechnologiesImage Retrieval and Classification TechniquesVideo Analysis and Summarization