Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200922694> ?p ?o ?g. }
- W3200922694 abstract "Automatic annotation of short-text data to a large number of target labels, referred to as Short Text Extreme Classification, has recently found numerous applications in prediction of related searches and product recommendation tasks. The conventional usage of Convolutional Neural Network (CNN) to capture n-grams in text-classification relies heavily on uniformity in word-ordering and the presence of long input sequences to convolve over. However, this is missing in short and unstructured text sequences encountered in search and recommendation. In order to tackle this, we propose an orthogonal approach by recasting the convolution operation to capture coupled semantics along the embedding dimensions, and develop a word-order agnostic embedding enhancement module to deal with the lack of structure in such queries. Benefitting from the computational efficiency of the convolution operation, Embedding Convolutions, when applied on the enriched word embeddings, result in a light-weight and yet powerful encoder (InceptionXML) that is robust to the inherent lack of structure in short-text extreme classification. Towards scaling our model to problems with millions of labels, we also propose InceptionXML+, which addresses the shortcomings of the dynamic hard-negative mining framework in the recently proposed LightXML by improving the alignment between the label-shortlister and extreme classifier. On popular benchmark datasets, we empirically demonstrate that the proposed method outperforms state-of-the-art deep extreme classifiers such as Astec by an average of 5% and 8% on the P@k and propensity-scored PSP@k metrics respectively." @default.
- W3200922694 created "2021-09-27" @default.
- W3200922694 creator A5015496269 @default.
- W3200922694 creator A5017545333 @default.
- W3200922694 creator A5021007371 @default.
- W3200922694 creator A5033114717 @default.
- W3200922694 date "2021-09-13" @default.
- W3200922694 modified "2023-09-27" @default.
- W3200922694 title "Embedding Convolutions for Short Text Extreme Classification with Millions of Labels" @default.
- W3200922694 cites W1832693441 @default.
- W3200922694 cites W1834987204 @default.
- W3200922694 cites W2068074736 @default.
- W3200922694 cites W2118585731 @default.
- W3200922694 cites W2183087644 @default.
- W3200922694 cites W2250539671 @default.
- W3200922694 cites W2362855512 @default.
- W3200922694 cites W2437817353 @default.
- W3200922694 cites W2461743311 @default.
- W3200922694 cites W2520348554 @default.
- W3200922694 cites W2739996966 @default.
- W3200922694 cites W2743021690 @default.
- W3200922694 cites W2788125153 @default.
- W3200922694 cites W2804078698 @default.
- W3200922694 cites W2890634844 @default.
- W3200922694 cites W2906963924 @default.
- W3200922694 cites W2921113176 @default.
- W3200922694 cites W2950344553 @default.
- W3200922694 cites W2963626623 @default.
- W3200922694 cites W2970574105 @default.
- W3200922694 cites W3034989857 @default.
- W3200922694 cites W3037422790 @default.
- W3200922694 cites W3080802002 @default.
- W3200922694 cites W3093858897 @default.
- W3200922694 cites W3099372209 @default.
- W3200922694 cites W3114079967 @default.
- W3200922694 cites W3117196003 @default.
- W3200922694 cites W3120689745 @default.
- W3200922694 cites W3152616003 @default.
- W3200922694 cites W3169488402 @default.
- W3200922694 cites W3170280507 @default.
- W3200922694 cites W3172352177 @default.
- W3200922694 hasPublicationYear "2021" @default.
- W3200922694 type Work @default.
- W3200922694 sameAs 3200922694 @default.
- W3200922694 citedByCount "0" @default.
- W3200922694 crossrefType "posted-content" @default.
- W3200922694 hasAuthorship W3200922694A5015496269 @default.
- W3200922694 hasAuthorship W3200922694A5017545333 @default.
- W3200922694 hasAuthorship W3200922694A5021007371 @default.
- W3200922694 hasAuthorship W3200922694A5033114717 @default.
- W3200922694 hasConcept C108583219 @default.
- W3200922694 hasConcept C124101348 @default.
- W3200922694 hasConcept C13280743 @default.
- W3200922694 hasConcept C153180895 @default.
- W3200922694 hasConcept C154945302 @default.
- W3200922694 hasConcept C185798385 @default.
- W3200922694 hasConcept C204321447 @default.
- W3200922694 hasConcept C205649164 @default.
- W3200922694 hasConcept C2524010 @default.
- W3200922694 hasConcept C2777462759 @default.
- W3200922694 hasConcept C33923547 @default.
- W3200922694 hasConcept C41008148 @default.
- W3200922694 hasConcept C41608201 @default.
- W3200922694 hasConcept C66402592 @default.
- W3200922694 hasConcept C81363708 @default.
- W3200922694 hasConcept C90805587 @default.
- W3200922694 hasConcept C95623464 @default.
- W3200922694 hasConceptScore W3200922694C108583219 @default.
- W3200922694 hasConceptScore W3200922694C124101348 @default.
- W3200922694 hasConceptScore W3200922694C13280743 @default.
- W3200922694 hasConceptScore W3200922694C153180895 @default.
- W3200922694 hasConceptScore W3200922694C154945302 @default.
- W3200922694 hasConceptScore W3200922694C185798385 @default.
- W3200922694 hasConceptScore W3200922694C204321447 @default.
- W3200922694 hasConceptScore W3200922694C205649164 @default.
- W3200922694 hasConceptScore W3200922694C2524010 @default.
- W3200922694 hasConceptScore W3200922694C2777462759 @default.
- W3200922694 hasConceptScore W3200922694C33923547 @default.
- W3200922694 hasConceptScore W3200922694C41008148 @default.
- W3200922694 hasConceptScore W3200922694C41608201 @default.
- W3200922694 hasConceptScore W3200922694C66402592 @default.
- W3200922694 hasConceptScore W3200922694C81363708 @default.
- W3200922694 hasConceptScore W3200922694C90805587 @default.
- W3200922694 hasConceptScore W3200922694C95623464 @default.
- W3200922694 hasLocation W32009226941 @default.
- W3200922694 hasOpenAccess W3200922694 @default.
- W3200922694 hasPrimaryLocation W32009226941 @default.
- W3200922694 hasRelatedWork W2159463015 @default.
- W3200922694 hasRelatedWork W2218741211 @default.
- W3200922694 hasRelatedWork W2479662217 @default.
- W3200922694 hasRelatedWork W2493727926 @default.
- W3200922694 hasRelatedWork W2744641177 @default.
- W3200922694 hasRelatedWork W2755005384 @default.
- W3200922694 hasRelatedWork W2787941686 @default.
- W3200922694 hasRelatedWork W2791396492 @default.
- W3200922694 hasRelatedWork W2883216965 @default.
- W3200922694 hasRelatedWork W2885902029 @default.
- W3200922694 hasRelatedWork W2946957311 @default.
- W3200922694 hasRelatedWork W2949235290 @default.
- W3200922694 hasRelatedWork W2952142541 @default.