Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129401410> ?p ?o ?g. }
- W3129401410 endingPage "963" @default.
- W3129401410 startingPage "911" @default.
- W3129401410 abstract "Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of this article) it seems appealing to enhance word representations with ad-hoc embeddings that encode task-specific information. We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially facilitate the training of deep-learning models in multiclass classification by topic. We show empirical evidence that WCEs yield a consistent improvement in multiclass classification accuracy, using six popular neural architectures and six widely used and publicly available datasets for multiclass text classification. One further advantage of this method is that it is conceptually simple and straightforward to implement. Our code that implements WCEs is publicly available at https://github.com/AlexMoreo/word-class-embeddings ." @default.
- W3129401410 created "2021-03-01" @default.
- W3129401410 creator A5063975186 @default.
- W3129401410 creator A5082069715 @default.
- W3129401410 creator A5086354805 @default.
- W3129401410 date "2021-02-19" @default.
- W3129401410 modified "2023-09-26" @default.
- W3129401410 title "Word-class embeddings for multiclass text classification" @default.
- W3129401410 cites W1498436455 @default.
- W3129401410 cites W1615991656 @default.
- W3129401410 cites W1832693441 @default.
- W3129401410 cites W1902237438 @default.
- W3129401410 cites W1978400666 @default.
- W3129401410 cites W1986913017 @default.
- W3129401410 cites W2034170092 @default.
- W3129401410 cites W2047021305 @default.
- W3129401410 cites W2064580901 @default.
- W3129401410 cites W2064675550 @default.
- W3129401410 cites W2105948726 @default.
- W3129401410 cites W2126502509 @default.
- W3129401410 cites W2140321362 @default.
- W3129401410 cites W2141253686 @default.
- W3129401410 cites W2147152072 @default.
- W3129401410 cites W2149684865 @default.
- W3129401410 cites W2158108973 @default.
- W3129401410 cites W2165849038 @default.
- W3129401410 cites W2170654002 @default.
- W3129401410 cites W2250539671 @default.
- W3129401410 cites W2251803266 @default.
- W3129401410 cites W2265846598 @default.
- W3129401410 cites W2287612586 @default.
- W3129401410 cites W2423124209 @default.
- W3129401410 cites W2493916176 @default.
- W3129401410 cites W2757560572 @default.
- W3129401410 cites W2910577570 @default.
- W3129401410 cites W2911379778 @default.
- W3129401410 cites W2918995630 @default.
- W3129401410 cites W2919115771 @default.
- W3129401410 cites W2940627316 @default.
- W3129401410 cites W2942326195 @default.
- W3129401410 cites W2945392649 @default.
- W3129401410 cites W2951559648 @default.
- W3129401410 cites W2962739339 @default.
- W3129401410 cites W2963626623 @default.
- W3129401410 cites W2963850840 @default.
- W3129401410 cites W2963910295 @default.
- W3129401410 cites W2963912736 @default.
- W3129401410 cites W2964236337 @default.
- W3129401410 cites W2990288623 @default.
- W3129401410 cites W2998914929 @default.
- W3129401410 cites W3098977645 @default.
- W3129401410 cites W3104717349 @default.
- W3129401410 cites W3157279044 @default.
- W3129401410 cites W3209042722 @default.
- W3129401410 cites W4205184193 @default.
- W3129401410 cites W4245322178 @default.
- W3129401410 cites W4288280763 @default.
- W3129401410 doi "https://doi.org/10.1007/s10618-020-00735-3" @default.
- W3129401410 hasPublicationYear "2021" @default.
- W3129401410 type Work @default.
- W3129401410 sameAs 3129401410 @default.
- W3129401410 citedByCount "24" @default.
- W3129401410 countsByYear W31294014102020 @default.
- W3129401410 countsByYear W31294014102021 @default.
- W3129401410 countsByYear W31294014102022 @default.
- W3129401410 countsByYear W31294014102023 @default.
- W3129401410 crossrefType "journal-article" @default.
- W3129401410 hasAuthorship W3129401410A5063975186 @default.
- W3129401410 hasAuthorship W3129401410A5082069715 @default.
- W3129401410 hasAuthorship W3129401410A5086354805 @default.
- W3129401410 hasBestOaLocation W31294014102 @default.
- W3129401410 hasConcept C104317684 @default.
- W3129401410 hasConcept C120665830 @default.
- W3129401410 hasConcept C121332964 @default.
- W3129401410 hasConcept C12267149 @default.
- W3129401410 hasConcept C123406163 @default.
- W3129401410 hasConcept C123860398 @default.
- W3129401410 hasConcept C154945302 @default.
- W3129401410 hasConcept C162324750 @default.
- W3129401410 hasConcept C184337299 @default.
- W3129401410 hasConcept C185592680 @default.
- W3129401410 hasConcept C187736073 @default.
- W3129401410 hasConcept C192209626 @default.
- W3129401410 hasConcept C199360897 @default.
- W3129401410 hasConcept C204321447 @default.
- W3129401410 hasConcept C2524010 @default.
- W3129401410 hasConcept C2776502983 @default.
- W3129401410 hasConcept C2777212361 @default.
- W3129401410 hasConcept C2780451532 @default.
- W3129401410 hasConcept C33923547 @default.
- W3129401410 hasConcept C41008148 @default.
- W3129401410 hasConcept C55493867 @default.
- W3129401410 hasConcept C66746571 @default.
- W3129401410 hasConcept C90805587 @default.
- W3129401410 hasConceptScore W3129401410C104317684 @default.
- W3129401410 hasConceptScore W3129401410C120665830 @default.
- W3129401410 hasConceptScore W3129401410C121332964 @default.
- W3129401410 hasConceptScore W3129401410C12267149 @default.