Matches in SemOpenAlex for { <https://semopenalex.org/work/W3183820005> ?p ?o ?g. }
- W3183820005 abstract "Word embeddings (e.g., word2vec) have been applied successfully to eCommerce products through prod2vec. Inspired by the recent performance improvements on several NLP tasks brought by contextualized embeddings, we propose to transfer BERT-like architectures to eCommerce: our model - Prod2BERT - is trained to generate representations of products through masked session modeling. Through extensive experiments over multiple shops, different tasks, and a range of design choices, we systematically compare the accuracy of Prod2BERT and prod2vec embeddings: while Prod2BERT is found to be superior in several scenarios, we highlight the importance of resources and hyperparameters in the best performing models. Finally, we provide guidelines to practitioners for training embeddings under a variety of computational and data constraints." @default.
- W3183820005 created "2021-08-02" @default.
- W3183820005 creator A5008079520 @default.
- W3183820005 creator A5069236966 @default.
- W3183820005 creator A5078515950 @default.
- W3183820005 date "2021-01-01" @default.
- W3183820005 modified "2023-10-14" @default.
- W3183820005 title "BERT Goes Shopping: Comparing Distributional Models for Product Representations" @default.
- W3183820005 cites W1491235195 @default.
- W3183820005 cites W1614298861 @default.
- W3183820005 cites W1615991656 @default.
- W3183820005 cites W1983578042 @default.
- W3183820005 cites W2250539671 @default.
- W3183820005 cites W2500403796 @default.
- W3183820005 cites W2582377823 @default.
- W3183820005 cites W2725049817 @default.
- W3183820005 cites W2776890924 @default.
- W3183820005 cites W2783877881 @default.
- W3183820005 cites W2797402435 @default.
- W3183820005 cites W2913153410 @default.
- W3183820005 cites W2951873305 @default.
- W3183820005 cites W2962756421 @default.
- W3183820005 cites W2962936818 @default.
- W3183820005 cites W2963118869 @default.
- W3183820005 cites W2963341956 @default.
- W3183820005 cites W2963403868 @default.
- W3183820005 cites W2963809228 @default.
- W3183820005 cites W2965373594 @default.
- W3183820005 cites W2970352191 @default.
- W3183820005 cites W2970476646 @default.
- W3183820005 cites W2984100107 @default.
- W3183820005 cites W2996428491 @default.
- W3183820005 cites W3001279689 @default.
- W3183820005 cites W3009095382 @default.
- W3183820005 cites W3034080962 @default.
- W3183820005 cites W3034445277 @default.
- W3183820005 cites W3034896171 @default.
- W3183820005 cites W3034969702 @default.
- W3183820005 cites W3041148953 @default.
- W3183820005 cites W3045557001 @default.
- W3183820005 cites W3045851136 @default.
- W3183820005 cites W3046131267 @default.
- W3183820005 cites W3088983215 @default.
- W3183820005 cites W3092306916 @default.
- W3183820005 cites W3099726625 @default.
- W3183820005 cites W3102116369 @default.
- W3183820005 cites W3105816068 @default.
- W3183820005 cites W3118485687 @default.
- W3183820005 cites W3120490999 @default.
- W3183820005 cites W3164378906 @default.
- W3183820005 cites W3168038263 @default.
- W3183820005 cites W3168655307 @default.
- W3183820005 cites W3175919386 @default.
- W3183820005 doi "https://doi.org/10.18653/v1/2021.ecnlp-1.1" @default.
- W3183820005 hasPublicationYear "2021" @default.
- W3183820005 type Work @default.
- W3183820005 sameAs 3183820005 @default.
- W3183820005 citedByCount "5" @default.
- W3183820005 countsByYear W31838200052021 @default.
- W3183820005 countsByYear W31838200052023 @default.
- W3183820005 crossrefType "proceedings-article" @default.
- W3183820005 hasAuthorship W3183820005A5008079520 @default.
- W3183820005 hasAuthorship W3183820005A5069236966 @default.
- W3183820005 hasAuthorship W3183820005A5078515950 @default.
- W3183820005 hasBestOaLocation W31838200051 @default.
- W3183820005 hasConcept C119857082 @default.
- W3183820005 hasConcept C136197465 @default.
- W3183820005 hasConcept C136764020 @default.
- W3183820005 hasConcept C138885662 @default.
- W3183820005 hasConcept C154945302 @default.
- W3183820005 hasConcept C159985019 @default.
- W3183820005 hasConcept C192562407 @default.
- W3183820005 hasConcept C204321447 @default.
- W3183820005 hasConcept C204323151 @default.
- W3183820005 hasConcept C2524010 @default.
- W3183820005 hasConcept C2776461190 @default.
- W3183820005 hasConcept C2779182362 @default.
- W3183820005 hasConcept C33923547 @default.
- W3183820005 hasConcept C41008148 @default.
- W3183820005 hasConcept C41608201 @default.
- W3183820005 hasConcept C41895202 @default.
- W3183820005 hasConcept C8642999 @default.
- W3183820005 hasConcept C90673727 @default.
- W3183820005 hasConcept C90805587 @default.
- W3183820005 hasConceptScore W3183820005C119857082 @default.
- W3183820005 hasConceptScore W3183820005C136197465 @default.
- W3183820005 hasConceptScore W3183820005C136764020 @default.
- W3183820005 hasConceptScore W3183820005C138885662 @default.
- W3183820005 hasConceptScore W3183820005C154945302 @default.
- W3183820005 hasConceptScore W3183820005C159985019 @default.
- W3183820005 hasConceptScore W3183820005C192562407 @default.
- W3183820005 hasConceptScore W3183820005C204321447 @default.
- W3183820005 hasConceptScore W3183820005C204323151 @default.
- W3183820005 hasConceptScore W3183820005C2524010 @default.
- W3183820005 hasConceptScore W3183820005C2776461190 @default.
- W3183820005 hasConceptScore W3183820005C2779182362 @default.
- W3183820005 hasConceptScore W3183820005C33923547 @default.
- W3183820005 hasConceptScore W3183820005C41008148 @default.
- W3183820005 hasConceptScore W3183820005C41608201 @default.
- W3183820005 hasConceptScore W3183820005C41895202 @default.