Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912255075> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2912255075 abstract "Recently a number of algorithms under the theme of 'unbiased learning-to-rank' have been proposed, which can reduce position bias, the major type of bias in click data, and train a high-performance ranker with click data. Most of the existing algorithms, based on the inverse propensity weighting (IPW) principle, first estimate the click bias at each position, and then train an unbiased ranker with the estimated biases using a learning-to-rank algorithm. However, there has not been a method for unbiased pairwise learning-to-rank that can simultaneously conduct debiasing of click data and training of a ranker using a pairwise loss function. In this paper, we propose a novel framework to accomplish the goal and apply this framework to the state-of-the-art pairwise learning-to-rank algorithm, LambdaMART. Our algorithm named Unbiased LambdaMART can jointly estimate the biases at click positions and the biases at unclick positions, and learn an unbiased ranker. Experiments on benchmark data show that Unbiased LambdaMART can significantly outperform existing algorithms by large margins. In addition, an online A/B Testing at a commercial search engine shows that Unbiased LambdaMART can effectively conduct debiasing of click data and enhance relevance ranking." @default.
- W2912255075 created "2019-02-21" @default.
- W2912255075 creator A5000322016 @default.
- W2912255075 creator A5003354149 @default.
- W2912255075 creator A5053676877 @default.
- W2912255075 creator A5060639952 @default.
- W2912255075 date "2019-05-13" @default.
- W2912255075 modified "2023-10-11" @default.
- W2912255075 title "Unbiased LambdaMART: An Unbiased Pairwise Learning-to-Rank Algorithm" @default.
- W2912255075 cites W1678356000 @default.
- W2912255075 cites W2069870183 @default.
- W2912255075 cites W2090883204 @default.
- W2912255075 cites W2149427297 @default.
- W2912255075 cites W2150291618 @default.
- W2912255075 cites W2152314154 @default.
- W2912255075 cites W2155587858 @default.
- W2912255075 cites W2162059449 @default.
- W2912255075 cites W2340526403 @default.
- W2912255075 cites W2507134384 @default.
- W2912255075 cites W2769473018 @default.
- W2912255075 cites W2797400361 @default.
- W2912255075 cites W2897785891 @default.
- W2912255075 doi "https://doi.org/10.1145/3308558.3313447" @default.
- W2912255075 hasPublicationYear "2019" @default.
- W2912255075 type Work @default.
- W2912255075 sameAs 2912255075 @default.
- W2912255075 citedByCount "44" @default.
- W2912255075 countsByYear W29122550752019 @default.
- W2912255075 countsByYear W29122550752020 @default.
- W2912255075 countsByYear W29122550752021 @default.
- W2912255075 countsByYear W29122550752022 @default.
- W2912255075 countsByYear W29122550752023 @default.
- W2912255075 crossrefType "proceedings-article" @default.
- W2912255075 hasAuthorship W2912255075A5000322016 @default.
- W2912255075 hasAuthorship W2912255075A5003354149 @default.
- W2912255075 hasAuthorship W2912255075A5053676877 @default.
- W2912255075 hasAuthorship W2912255075A5060639952 @default.
- W2912255075 hasBestOaLocation W29122550751 @default.
- W2912255075 hasConcept C11413529 @default.
- W2912255075 hasConcept C114614502 @default.
- W2912255075 hasConcept C119857082 @default.
- W2912255075 hasConcept C13280743 @default.
- W2912255075 hasConcept C154945302 @default.
- W2912255075 hasConcept C15744967 @default.
- W2912255075 hasConcept C164226766 @default.
- W2912255075 hasConcept C184898388 @default.
- W2912255075 hasConcept C185798385 @default.
- W2912255075 hasConcept C188147891 @default.
- W2912255075 hasConcept C189430467 @default.
- W2912255075 hasConcept C205649164 @default.
- W2912255075 hasConcept C2779458634 @default.
- W2912255075 hasConcept C33923547 @default.
- W2912255075 hasConcept C41008148 @default.
- W2912255075 hasConcept C86037889 @default.
- W2912255075 hasConceptScore W2912255075C11413529 @default.
- W2912255075 hasConceptScore W2912255075C114614502 @default.
- W2912255075 hasConceptScore W2912255075C119857082 @default.
- W2912255075 hasConceptScore W2912255075C13280743 @default.
- W2912255075 hasConceptScore W2912255075C154945302 @default.
- W2912255075 hasConceptScore W2912255075C15744967 @default.
- W2912255075 hasConceptScore W2912255075C164226766 @default.
- W2912255075 hasConceptScore W2912255075C184898388 @default.
- W2912255075 hasConceptScore W2912255075C185798385 @default.
- W2912255075 hasConceptScore W2912255075C188147891 @default.
- W2912255075 hasConceptScore W2912255075C189430467 @default.
- W2912255075 hasConceptScore W2912255075C205649164 @default.
- W2912255075 hasConceptScore W2912255075C2779458634 @default.
- W2912255075 hasConceptScore W2912255075C33923547 @default.
- W2912255075 hasConceptScore W2912255075C41008148 @default.
- W2912255075 hasConceptScore W2912255075C86037889 @default.
- W2912255075 hasLocation W29122550751 @default.
- W2912255075 hasLocation W29122550752 @default.
- W2912255075 hasOpenAccess W2912255075 @default.
- W2912255075 hasPrimaryLocation W29122550751 @default.
- W2912255075 hasRelatedWork W1786507113 @default.
- W2912255075 hasRelatedWork W2039826537 @default.
- W2912255075 hasRelatedWork W2048843004 @default.
- W2912255075 hasRelatedWork W2096682819 @default.
- W2912255075 hasRelatedWork W2104465941 @default.
- W2912255075 hasRelatedWork W2293317945 @default.
- W2912255075 hasRelatedWork W2979827194 @default.
- W2912255075 hasRelatedWork W4288093608 @default.
- W2912255075 hasRelatedWork W4318960487 @default.
- W2912255075 hasRelatedWork W4323349240 @default.
- W2912255075 isParatext "false" @default.
- W2912255075 isRetracted "false" @default.
- W2912255075 magId "2912255075" @default.
- W2912255075 workType "article" @default.