Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950934423> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2950934423 abstract "Recently, several deep learning models have been successfully proposed and have been applied to solve different Natural Language Processing (NLP) tasks. However, these models solve the problem based on single-task supervised learning and do not consider the correlation between the tasks. Based on this observation, in this paper, we implemented a multi-task learning model to joint learn two related NLP tasks simultaneously and conducted experiments to evaluate if learning these tasks jointly can improve the system performance compared with learning them individually. In addition, a comparison of our model with the state-of-the-art learning models, including multi-task learning, transfer learning, unsupervised learning and feature based traditional machine learning models is presented. This paper aims to 1) show the advantage of multi-task learning over single-task learning in training related NLP tasks, 2) illustrate the influence of various encoding structures to the proposed single- and multi-task learning models, and 3) compare the performance between multi-task learning and other learning models in literature on textual entailment task and semantic relatedness task." @default.
- W2950934423 created "2019-06-27" @default.
- W2950934423 creator A5043094101 @default.
- W2950934423 creator A5045272072 @default.
- W2950934423 date "2019-01-01" @default.
- W2950934423 modified "2023-10-17" @default.
- W2950934423 title "Multi-Task Learning for Semantic Relatedness and Textual Entailment" @default.
- W2950934423 cites W2064675550 @default.
- W2950934423 cites W2117130368 @default.
- W2950934423 cites W2131774270 @default.
- W2950934423 cites W2144354855 @default.
- W2950934423 cites W2251919380 @default.
- W2950934423 cites W2493916176 @default.
- W2950934423 cites W2516255829 @default.
- W2950934423 cites W2526425061 @default.
- W2950934423 cites W2556468274 @default.
- W2950934423 cites W2597655663 @default.
- W2950934423 cites W2624871570 @default.
- W2950934423 cites W2742079690 @default.
- W2950934423 cites W2751762827 @default.
- W2950934423 cites W2798405286 @default.
- W2950934423 cites W2913340405 @default.
- W2950934423 cites W2963266252 @default.
- W2950934423 cites W2963355447 @default.
- W2950934423 cites W2963677766 @default.
- W2950934423 cites W2964121744 @default.
- W2950934423 cites W582055897 @default.
- W2950934423 doi "https://doi.org/10.4236/jsea.2019.126012" @default.
- W2950934423 hasPublicationYear "2019" @default.
- W2950934423 type Work @default.
- W2950934423 sameAs 2950934423 @default.
- W2950934423 citedByCount "0" @default.
- W2950934423 crossrefType "journal-article" @default.
- W2950934423 hasAuthorship W2950934423A5043094101 @default.
- W2950934423 hasAuthorship W2950934423A5045272072 @default.
- W2950934423 hasBestOaLocation W29509344231 @default.
- W2950934423 hasConcept C108583219 @default.
- W2950934423 hasConcept C119857082 @default.
- W2950934423 hasConcept C134752490 @default.
- W2950934423 hasConcept C138885662 @default.
- W2950934423 hasConcept C150899416 @default.
- W2950934423 hasConcept C154945302 @default.
- W2950934423 hasConcept C162324750 @default.
- W2950934423 hasConcept C187736073 @default.
- W2950934423 hasConcept C204321447 @default.
- W2950934423 hasConcept C24138899 @default.
- W2950934423 hasConcept C2776401178 @default.
- W2950934423 hasConcept C2780451532 @default.
- W2950934423 hasConcept C28006648 @default.
- W2950934423 hasConcept C41008148 @default.
- W2950934423 hasConcept C41895202 @default.
- W2950934423 hasConcept C58973888 @default.
- W2950934423 hasConcept C59404180 @default.
- W2950934423 hasConcept C8038995 @default.
- W2950934423 hasConcept C95318506 @default.
- W2950934423 hasConceptScore W2950934423C108583219 @default.
- W2950934423 hasConceptScore W2950934423C119857082 @default.
- W2950934423 hasConceptScore W2950934423C134752490 @default.
- W2950934423 hasConceptScore W2950934423C138885662 @default.
- W2950934423 hasConceptScore W2950934423C150899416 @default.
- W2950934423 hasConceptScore W2950934423C154945302 @default.
- W2950934423 hasConceptScore W2950934423C162324750 @default.
- W2950934423 hasConceptScore W2950934423C187736073 @default.
- W2950934423 hasConceptScore W2950934423C204321447 @default.
- W2950934423 hasConceptScore W2950934423C24138899 @default.
- W2950934423 hasConceptScore W2950934423C2776401178 @default.
- W2950934423 hasConceptScore W2950934423C2780451532 @default.
- W2950934423 hasConceptScore W2950934423C28006648 @default.
- W2950934423 hasConceptScore W2950934423C41008148 @default.
- W2950934423 hasConceptScore W2950934423C41895202 @default.
- W2950934423 hasConceptScore W2950934423C58973888 @default.
- W2950934423 hasConceptScore W2950934423C59404180 @default.
- W2950934423 hasConceptScore W2950934423C8038995 @default.
- W2950934423 hasConceptScore W2950934423C95318506 @default.
- W2950934423 hasLocation W29509344231 @default.
- W2950934423 hasOpenAccess W2950934423 @default.
- W2950934423 hasPrimaryLocation W29509344231 @default.
- W2950934423 hasRelatedWork W2186489521 @default.
- W2950934423 hasRelatedWork W2597787948 @default.
- W2950934423 hasRelatedWork W2896257747 @default.
- W2950934423 hasRelatedWork W2908875379 @default.
- W2950934423 hasRelatedWork W2950934423 @default.
- W2950934423 hasRelatedWork W2951786554 @default.
- W2950934423 hasRelatedWork W2963218179 @default.
- W2950934423 hasRelatedWork W3006989712 @default.
- W2950934423 hasRelatedWork W3095538999 @default.
- W2950934423 hasRelatedWork W4206984194 @default.
- W2950934423 isParatext "false" @default.
- W2950934423 isRetracted "false" @default.
- W2950934423 magId "2950934423" @default.
- W2950934423 workType "article" @default.