Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904728018> ?p ?o ?g. }
- W2904728018 abstract "E-commerce platforms categorize their products into a multi-level taxonomy tree with thousands of leaf categories. Conventional methods for product categorization are typically based on machine learning classification algorithms. These algorithms take product information as input (e.g., titles and descriptions) to classify a product into a leaf category. In this paper, we propose a new paradigm based on machine translation. In our approach, we translate a product's natural language description into a sequence of tokens representing a root-to-leaf path in a product taxonomy. In our experiments on two large real-world datasets, we show that our approach achieves better predictive accuracy than a state-of-the-art classification system for product categorization. In addition, we demonstrate that our machine translation models can propose meaningful new paths between previously unconnected nodes in a taxonomy tree, thereby transforming the taxonomy into a directed acyclic graph (DAG). We discuss how the resultant taxonomy DAG promotes user-friendly navigation, and how it is more adaptable to new products." @default.
- W2904728018 created "2018-12-22" @default.
- W2904728018 creator A5013720432 @default.
- W2904728018 creator A5019013403 @default.
- W2904728018 creator A5031800911 @default.
- W2904728018 date "2018-12-14" @default.
- W2904728018 modified "2023-09-27" @default.
- W2904728018 title "Don't Classify, Translate: Multi-Level E-Commerce Product Categorization Via Machine Translation" @default.
- W2904728018 cites W1678356000 @default.
- W2904728018 cites W1753482797 @default.
- W2904728018 cites W1880262756 @default.
- W2904728018 cites W1968153682 @default.
- W2904728018 cites W2017215520 @default.
- W2904728018 cites W2027080615 @default.
- W2904728018 cites W2051840895 @default.
- W2904728018 cites W2064675550 @default.
- W2904728018 cites W2100495367 @default.
- W2904728018 cites W2112796928 @default.
- W2904728018 cites W2119821739 @default.
- W2904728018 cites W2131420021 @default.
- W2904728018 cites W2136922672 @default.
- W2904728018 cites W2143774383 @default.
- W2904728018 cites W2157331557 @default.
- W2904728018 cites W2293569829 @default.
- W2904728018 cites W2510938745 @default.
- W2904728018 cites W2557283755 @default.
- W2904728018 cites W2579710467 @default.
- W2904728018 cites W2584417445 @default.
- W2904728018 cites W2626778328 @default.
- W2904728018 cites W2741511332 @default.
- W2904728018 cites W2757291580 @default.
- W2904728018 cites W2767829409 @default.
- W2904728018 cites W2794365787 @default.
- W2904728018 cites W2920313468 @default.
- W2904728018 cites W2949335953 @default.
- W2904728018 cites W2949888546 @default.
- W2904728018 cites W2949988325 @default.
- W2904728018 cites W2950133940 @default.
- W2904728018 cites W2964199361 @default.
- W2904728018 cites W3098649723 @default.
- W2904728018 hasPublicationYear "2018" @default.
- W2904728018 type Work @default.
- W2904728018 sameAs 2904728018 @default.
- W2904728018 citedByCount "3" @default.
- W2904728018 countsByYear W29047280182019 @default.
- W2904728018 countsByYear W29047280182020 @default.
- W2904728018 crossrefType "posted-content" @default.
- W2904728018 hasAuthorship W2904728018A5013720432 @default.
- W2904728018 hasAuthorship W2904728018A5019013403 @default.
- W2904728018 hasAuthorship W2904728018A5031800911 @default.
- W2904728018 hasConcept C113174947 @default.
- W2904728018 hasConcept C11413529 @default.
- W2904728018 hasConcept C119857082 @default.
- W2904728018 hasConcept C124101348 @default.
- W2904728018 hasConcept C132525143 @default.
- W2904728018 hasConcept C134306372 @default.
- W2904728018 hasConcept C154945302 @default.
- W2904728018 hasConcept C203005215 @default.
- W2904728018 hasConcept C204321447 @default.
- W2904728018 hasConcept C23123220 @default.
- W2904728018 hasConcept C2524010 @default.
- W2904728018 hasConcept C33923547 @default.
- W2904728018 hasConcept C41008148 @default.
- W2904728018 hasConcept C58642233 @default.
- W2904728018 hasConcept C59822182 @default.
- W2904728018 hasConcept C74197172 @default.
- W2904728018 hasConcept C80444323 @default.
- W2904728018 hasConcept C86803240 @default.
- W2904728018 hasConcept C90673727 @default.
- W2904728018 hasConcept C94124525 @default.
- W2904728018 hasConceptScore W2904728018C113174947 @default.
- W2904728018 hasConceptScore W2904728018C11413529 @default.
- W2904728018 hasConceptScore W2904728018C119857082 @default.
- W2904728018 hasConceptScore W2904728018C124101348 @default.
- W2904728018 hasConceptScore W2904728018C132525143 @default.
- W2904728018 hasConceptScore W2904728018C134306372 @default.
- W2904728018 hasConceptScore W2904728018C154945302 @default.
- W2904728018 hasConceptScore W2904728018C203005215 @default.
- W2904728018 hasConceptScore W2904728018C204321447 @default.
- W2904728018 hasConceptScore W2904728018C23123220 @default.
- W2904728018 hasConceptScore W2904728018C2524010 @default.
- W2904728018 hasConceptScore W2904728018C33923547 @default.
- W2904728018 hasConceptScore W2904728018C41008148 @default.
- W2904728018 hasConceptScore W2904728018C58642233 @default.
- W2904728018 hasConceptScore W2904728018C59822182 @default.
- W2904728018 hasConceptScore W2904728018C74197172 @default.
- W2904728018 hasConceptScore W2904728018C80444323 @default.
- W2904728018 hasConceptScore W2904728018C86803240 @default.
- W2904728018 hasConceptScore W2904728018C90673727 @default.
- W2904728018 hasConceptScore W2904728018C94124525 @default.
- W2904728018 hasLocation W29047280181 @default.
- W2904728018 hasOpenAccess W2904728018 @default.
- W2904728018 hasPrimaryLocation W29047280181 @default.
- W2904728018 hasRelatedWork W1504471463 @default.
- W2904728018 hasRelatedWork W1909353682 @default.
- W2904728018 hasRelatedWork W1969221592 @default.
- W2904728018 hasRelatedWork W1989831993 @default.
- W2904728018 hasRelatedWork W2023186333 @default.
- W2904728018 hasRelatedWork W2098728436 @default.
- W2904728018 hasRelatedWork W2125682865 @default.