Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890225654> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2890225654 abstract "Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic knowledge. Moreover, embeddings are often built from a single source of information (typically text data), even though neurocognitive research suggests that semantics is deeply linked to both language and perception. In this paper, we combine multimodal information from both text and image-based representations derived from state-of-the-art distributional models to produce sparse, interpretable vectors using Joint Non-Negative Sparse Embedding. Through in-depth analyses comparing these sparse models to human-derived behavioural and neuroimaging data, we demonstrate their ability to predict interpretable linguistic descriptions of human ground-truth semantic knowledge." @default.
- W2890225654 created "2018-09-27" @default.
- W2890225654 creator A5007017103 @default.
- W2890225654 creator A5018008959 @default.
- W2890225654 creator A5029850297 @default.
- W2890225654 creator A5068876836 @default.
- W2890225654 date "2018-09-07" @default.
- W2890225654 modified "2023-09-26" @default.
- W2890225654 title "Using Sparse Semantic Embeddings Learned from Multimodal Text and Image Data to Model Human Conceptual Knowledge" @default.
- W2890225654 cites W1789976143 @default.
- W2890225654 cites W1854884267 @default.
- W2890225654 cites W1965580172 @default.
- W2890225654 cites W1972611943 @default.
- W2890225654 cites W2067438047 @default.
- W2890225654 cites W2081580037 @default.
- W2890225654 cites W2089632738 @default.
- W2890225654 cites W2108469855 @default.
- W2890225654 cites W2108598243 @default.
- W2890225654 cites W2112184938 @default.
- W2890225654 cites W2112447569 @default.
- W2890225654 cites W2116216716 @default.
- W2890225654 cites W2137735870 @default.
- W2890225654 cites W2141282920 @default.
- W2890225654 cites W2145056192 @default.
- W2890225654 cites W2161381512 @default.
- W2890225654 cites W2184188583 @default.
- W2890225654 cites W2250539671 @default.
- W2890225654 cites W2252057887 @default.
- W2890225654 cites W2344975321 @default.
- W2890225654 cites W2502814102 @default.
- W2890225654 cites W2512498397 @default.
- W2890225654 cites W2517394272 @default.
- W2890225654 cites W2559169016 @default.
- W2890225654 cites W2563767109 @default.
- W2890225654 cites W2568389463 @default.
- W2890225654 cites W2570058081 @default.
- W2890225654 cites W2619269940 @default.
- W2890225654 cites W2797270586 @default.
- W2890225654 cites W2949291345 @default.
- W2890225654 cites W2950133940 @default.
- W2890225654 cites W2950761309 @default.
- W2890225654 cites W2952186574 @default.
- W2890225654 cites W2963871344 @default.
- W2890225654 cites W810147176 @default.
- W2890225654 hasPublicationYear "2018" @default.
- W2890225654 type Work @default.
- W2890225654 sameAs 2890225654 @default.
- W2890225654 citedByCount "0" @default.
- W2890225654 crossrefType "posted-content" @default.
- W2890225654 hasAuthorship W2890225654A5007017103 @default.
- W2890225654 hasAuthorship W2890225654A5018008959 @default.
- W2890225654 hasAuthorship W2890225654A5029850297 @default.
- W2890225654 hasAuthorship W2890225654A5068876836 @default.
- W2890225654 hasConcept C115961682 @default.
- W2890225654 hasConcept C154945302 @default.
- W2890225654 hasConcept C184337299 @default.
- W2890225654 hasConcept C199360897 @default.
- W2890225654 hasConcept C204321447 @default.
- W2890225654 hasConcept C41008148 @default.
- W2890225654 hasConcept C41608201 @default.
- W2890225654 hasConceptScore W2890225654C115961682 @default.
- W2890225654 hasConceptScore W2890225654C154945302 @default.
- W2890225654 hasConceptScore W2890225654C184337299 @default.
- W2890225654 hasConceptScore W2890225654C199360897 @default.
- W2890225654 hasConceptScore W2890225654C204321447 @default.
- W2890225654 hasConceptScore W2890225654C41008148 @default.
- W2890225654 hasConceptScore W2890225654C41608201 @default.
- W2890225654 hasLocation W28902256541 @default.
- W2890225654 hasOpenAccess W2890225654 @default.
- W2890225654 hasPrimaryLocation W28902256541 @default.
- W2890225654 hasRelatedWork W1758944695 @default.
- W2890225654 hasRelatedWork W2112184938 @default.
- W2890225654 hasRelatedWork W2186101622 @default.
- W2890225654 hasRelatedWork W2251268966 @default.
- W2890225654 hasRelatedWork W2251311611 @default.
- W2890225654 hasRelatedWork W2785638793 @default.
- W2890225654 hasRelatedWork W2892282605 @default.
- W2890225654 hasRelatedWork W2949402715 @default.
- W2890225654 hasRelatedWork W2965215977 @default.
- W2890225654 hasRelatedWork W2970905328 @default.
- W2890225654 hasRelatedWork W2976980910 @default.
- W2890225654 hasRelatedWork W2980806730 @default.
- W2890225654 hasRelatedWork W2998363596 @default.
- W2890225654 hasRelatedWork W3093623420 @default.
- W2890225654 hasRelatedWork W3094563638 @default.
- W2890225654 hasRelatedWork W3113032096 @default.
- W2890225654 hasRelatedWork W3127237033 @default.
- W2890225654 hasRelatedWork W3185952614 @default.
- W2890225654 hasRelatedWork W2337036940 @default.
- W2890225654 hasRelatedWork W3187724475 @default.
- W2890225654 isParatext "false" @default.
- W2890225654 isRetracted "false" @default.
- W2890225654 magId "2890225654" @default.
- W2890225654 workType "article" @default.