Matches in SemOpenAlex for { <https://semopenalex.org/work/W2728346985> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2728346985 abstract "Predicting the click-through rate of an advertisement is a critical component of online advertising platforms. In sponsored search, the click-through rate estimates the probability that a displayed advertisement is clicked by a user after she submits a query to the search engine. Commercial search engines typically rely on machine learning models trained with a large number of features to make such predictions. This inevitably requires a lot of engineering efforts to define, compute, and select the appropriate features. In this paper, we propose two novel approaches (one working at character level and the other working at word level) that use deep convolutional neural networks to predict the click-through rate of a query-advertisement pair. Specifically, the proposed architectures only consider the textual content appearing in a query-advertisement pair as input, and produce as output a click-through rate prediction. By comparing the character-level model with the word-level model, we show that language representation can be learnt from scratch at character level when trained on enough data. Through extensive experiments using billions of query-advertisement pairs of a popular commercial search engine, we demonstrate that both approaches significantly outperform a baseline model built on well-selected text features and a state-of-the-art word2vec-based approach. Finally, by combining the predictions of the deep models introduced in this study with the prediction of the model in production of the same commercial search engine, we significantly improve the accuracy and the calibration of the click-through rate prediction of the production system." @default.
- W2728346985 created "2017-07-14" @default.
- W2728346985 creator A5003231629 @default.
- W2728346985 creator A5026874866 @default.
- W2728346985 creator A5059385158 @default.
- W2728346985 date "2017-08-07" @default.
- W2728346985 modified "2023-10-18" @default.
- W2728346985 title "Deep Character-Level Click-Through Rate Prediction for Sponsored Search" @default.
- W2728346985 cites W1677182931 @default.
- W2728346985 cites W1860935423 @default.
- W2728346985 cites W1981976602 @default.
- W2728346985 cites W2053323136 @default.
- W2728346985 cites W2073880140 @default.
- W2728346985 cites W2539224399 @default.
- W2728346985 doi "https://doi.org/10.1145/3077136.3080811" @default.
- W2728346985 hasPublicationYear "2017" @default.
- W2728346985 type Work @default.
- W2728346985 sameAs 2728346985 @default.
- W2728346985 citedByCount "21" @default.
- W2728346985 countsByYear W27283469852018 @default.
- W2728346985 countsByYear W27283469852019 @default.
- W2728346985 countsByYear W27283469852020 @default.
- W2728346985 countsByYear W27283469852021 @default.
- W2728346985 countsByYear W27283469852022 @default.
- W2728346985 countsByYear W27283469852023 @default.
- W2728346985 crossrefType "proceedings-article" @default.
- W2728346985 hasAuthorship W2728346985A5003231629 @default.
- W2728346985 hasAuthorship W2728346985A5026874866 @default.
- W2728346985 hasAuthorship W2728346985A5059385158 @default.
- W2728346985 hasBestOaLocation W27283469852 @default.
- W2728346985 hasConcept C108583219 @default.
- W2728346985 hasConcept C115174607 @default.
- W2728346985 hasConcept C119857082 @default.
- W2728346985 hasConcept C124101348 @default.
- W2728346985 hasConcept C137293760 @default.
- W2728346985 hasConcept C138885662 @default.
- W2728346985 hasConcept C154945302 @default.
- W2728346985 hasConcept C17744445 @default.
- W2728346985 hasConcept C199539241 @default.
- W2728346985 hasConcept C204321447 @default.
- W2728346985 hasConcept C23123220 @default.
- W2728346985 hasConcept C2524010 @default.
- W2728346985 hasConcept C25343380 @default.
- W2728346985 hasConcept C2776359362 @default.
- W2728346985 hasConcept C2776461190 @default.
- W2728346985 hasConcept C2780861071 @default.
- W2728346985 hasConcept C33923547 @default.
- W2728346985 hasConcept C41008148 @default.
- W2728346985 hasConcept C41608201 @default.
- W2728346985 hasConcept C41895202 @default.
- W2728346985 hasConcept C81363708 @default.
- W2728346985 hasConcept C90805587 @default.
- W2728346985 hasConcept C94625758 @default.
- W2728346985 hasConcept C97854310 @default.
- W2728346985 hasConceptScore W2728346985C108583219 @default.
- W2728346985 hasConceptScore W2728346985C115174607 @default.
- W2728346985 hasConceptScore W2728346985C119857082 @default.
- W2728346985 hasConceptScore W2728346985C124101348 @default.
- W2728346985 hasConceptScore W2728346985C137293760 @default.
- W2728346985 hasConceptScore W2728346985C138885662 @default.
- W2728346985 hasConceptScore W2728346985C154945302 @default.
- W2728346985 hasConceptScore W2728346985C17744445 @default.
- W2728346985 hasConceptScore W2728346985C199539241 @default.
- W2728346985 hasConceptScore W2728346985C204321447 @default.
- W2728346985 hasConceptScore W2728346985C23123220 @default.
- W2728346985 hasConceptScore W2728346985C2524010 @default.
- W2728346985 hasConceptScore W2728346985C25343380 @default.
- W2728346985 hasConceptScore W2728346985C2776359362 @default.
- W2728346985 hasConceptScore W2728346985C2776461190 @default.
- W2728346985 hasConceptScore W2728346985C2780861071 @default.
- W2728346985 hasConceptScore W2728346985C33923547 @default.
- W2728346985 hasConceptScore W2728346985C41008148 @default.
- W2728346985 hasConceptScore W2728346985C41608201 @default.
- W2728346985 hasConceptScore W2728346985C41895202 @default.
- W2728346985 hasConceptScore W2728346985C81363708 @default.
- W2728346985 hasConceptScore W2728346985C90805587 @default.
- W2728346985 hasConceptScore W2728346985C94625758 @default.
- W2728346985 hasConceptScore W2728346985C97854310 @default.
- W2728346985 hasLocation W27283469851 @default.
- W2728346985 hasLocation W27283469852 @default.
- W2728346985 hasLocation W27283469853 @default.
- W2728346985 hasOpenAccess W2728346985 @default.
- W2728346985 hasPrimaryLocation W27283469851 @default.
- W2728346985 hasRelatedWork W2346530426 @default.
- W2728346985 hasRelatedWork W2772765860 @default.
- W2728346985 hasRelatedWork W2890749918 @default.
- W2728346985 hasRelatedWork W2905749112 @default.
- W2728346985 hasRelatedWork W2944691285 @default.
- W2728346985 hasRelatedWork W3046869600 @default.
- W2728346985 hasRelatedWork W3099354896 @default.
- W2728346985 hasRelatedWork W3101154008 @default.
- W2728346985 hasRelatedWork W4287599800 @default.
- W2728346985 hasRelatedWork W4312264180 @default.
- W2728346985 isParatext "false" @default.
- W2728346985 isRetracted "false" @default.
- W2728346985 magId "2728346985" @default.
- W2728346985 workType "article" @default.