SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945392649> ?p ?o ?g. }

Showing items 1 to 87 of 87 with 100 items per page.

W2945392649 endingPage "569" @default.
W2945392649 startingPage "563" @default.
W2945392649 abstract "Over the past few years, the use of pre-trained word embeddings to solve natural language processing tasks has considerably improved performances on every end. However, even though these embeddings are trained on gigantic corpora, the vocabulary is fixed and thus numerous out of vocabulary words appear in specific downstream tasks. Recent studies proposed models able to generate embeddings for out of vocabulary words given its morphology and its context. These models assume that we have sufficient textual data in hand to train them. In contrast, we specifically tackle the case where such data is not available anymore and we rely only on pre-trained embeddings. As a solution, we introduce a model that predicts meaningful embeddings from the spelling of a word as well as from the context in which it appears for a downstream task without the need of pre-training on a given corpus. We thoroughly test our model on a joint tagging task on three different languages. Results show that our model helps consistently on all languages, outperforms other ways of handling out of vocabulary words and can be integrated into any neural model to predict out of vocabulary words." @default.
W2945392649 created "2019-05-29" @default.
W2945392649 creator A5001334643 @default.
W2945392649 creator A5035170980 @default.
W2945392649 creator A5090834942 @default.
W2945392649 date "2019-01-01" @default.
W2945392649 modified "2023-09-27" @default.
W2945392649 title "Contextual Generation of Word Embeddings for Out of Vocabulary Words in Downstream Tasks" @default.
W2945392649 cites W1677182931 @default.
W2945392649 cites W1899794420 @default.
W2945392649 cites W2301095666 @default.
W2945392649 cites W2493916176 @default.
W2945392649 cites W2891680269 @default.
W2945392649 cites W2962688369 @default.
W2945392649 cites W2962739339 @default.
W2945392649 cites W2963421945 @default.
W2945392649 cites W4210984920 @default.
W2945392649 doi "https://doi.org/10.1007/978-3-030-18305-9_60" @default.
W2945392649 hasPublicationYear "2019" @default.
W2945392649 type Work @default.
W2945392649 sameAs 2945392649 @default.
W2945392649 citedByCount "5" @default.
W2945392649 countsByYear W29453926492019 @default.
W2945392649 countsByYear W29453926492020 @default.
W2945392649 countsByYear W29453926492021 @default.
W2945392649 countsByYear W29453926492022 @default.
W2945392649 crossrefType "book-chapter" @default.
W2945392649 hasAuthorship W2945392649A5001334643 @default.
W2945392649 hasAuthorship W2945392649A5035170980 @default.
W2945392649 hasAuthorship W2945392649A5090834942 @default.
W2945392649 hasConcept C137293760 @default.
W2945392649 hasConcept C138885662 @default.
W2945392649 hasConcept C151730666 @default.
W2945392649 hasConcept C154945302 @default.
W2945392649 hasConcept C162324750 @default.
W2945392649 hasConcept C187736073 @default.
W2945392649 hasConcept C204321447 @default.
W2945392649 hasConcept C21547014 @default.
W2945392649 hasConcept C2776207758 @default.
W2945392649 hasConcept C2776502983 @default.
W2945392649 hasConcept C2777601683 @default.
W2945392649 hasConcept C2777801307 @default.
W2945392649 hasConcept C2779343474 @default.
W2945392649 hasConcept C2780451532 @default.
W2945392649 hasConcept C28490314 @default.
W2945392649 hasConcept C41008148 @default.
W2945392649 hasConcept C41895202 @default.
W2945392649 hasConcept C86803240 @default.
W2945392649 hasConcept C90805587 @default.
W2945392649 hasConceptScore W2945392649C137293760 @default.
W2945392649 hasConceptScore W2945392649C138885662 @default.
W2945392649 hasConceptScore W2945392649C151730666 @default.
W2945392649 hasConceptScore W2945392649C154945302 @default.
W2945392649 hasConceptScore W2945392649C162324750 @default.
W2945392649 hasConceptScore W2945392649C187736073 @default.
W2945392649 hasConceptScore W2945392649C204321447 @default.
W2945392649 hasConceptScore W2945392649C21547014 @default.
W2945392649 hasConceptScore W2945392649C2776207758 @default.
W2945392649 hasConceptScore W2945392649C2776502983 @default.
W2945392649 hasConceptScore W2945392649C2777601683 @default.
W2945392649 hasConceptScore W2945392649C2777801307 @default.
W2945392649 hasConceptScore W2945392649C2779343474 @default.
W2945392649 hasConceptScore W2945392649C2780451532 @default.
W2945392649 hasConceptScore W2945392649C28490314 @default.
W2945392649 hasConceptScore W2945392649C41008148 @default.
W2945392649 hasConceptScore W2945392649C41895202 @default.
W2945392649 hasConceptScore W2945392649C86803240 @default.
W2945392649 hasConceptScore W2945392649C90805587 @default.
W2945392649 hasLocation W29453926491 @default.
W2945392649 hasOpenAccess W2945392649 @default.
W2945392649 hasPrimaryLocation W29453926491 @default.
W2945392649 hasRelatedWork W1508636238 @default.
W2945392649 hasRelatedWork W2062636460 @default.
W2945392649 hasRelatedWork W2250374950 @default.
W2945392649 hasRelatedWork W2945392649 @default.
W2945392649 hasRelatedWork W2973863557 @default.
W2945392649 hasRelatedWork W3107474891 @default.
W2945392649 hasRelatedWork W3115808059 @default.
W2945392649 hasRelatedWork W3119155061 @default.
W2945392649 hasRelatedWork W4287548803 @default.
W2945392649 hasRelatedWork W4290056478 @default.
W2945392649 isParatext "false" @default.
W2945392649 isRetracted "false" @default.
W2945392649 magId "2945392649" @default.
W2945392649 workType "book-chapter" @default.