Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285282124> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4285282124 abstract "Distributional semantic models capture word-level meaning that is useful in many natural language processing tasks and have even been shown to capture cognitive aspects of word meaning. The majority of these models are purely text based, even though the human sensory experience is much richer. In this paper we create visually grounded word embeddings by combining English text and images and compare them to popular text-based methods, to see if visual information allows our model to better capture cognitive aspects of word meaning. Our analysis shows that visually grounded embedding similarities are more predictive of the human reaction times in a large priming experiment than the purely text-based embeddings. The visually grounded embeddings also correlate well with human word similarity ratings. Importantly, in both experiments we show that the grounded embeddings account for a unique portion of explained variance, even when we include text-based embeddings trained on huge corpora. This shows that visual grounding allows our model to capture information that cannot be extracted using text as the only source of information." @default.
- W4285282124 created "2022-07-14" @default.
- W4285282124 creator A5032091280 @default.
- W4285282124 creator A5076704114 @default.
- W4285282124 creator A5091677603 @default.
- W4285282124 date "2022-01-01" @default.
- W4285282124 modified "2023-09-25" @default.
- W4285282124 title "Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge" @default.
- W4285282124 doi "https://doi.org/10.18653/v1/2022.cmcl-1.1" @default.
- W4285282124 hasPublicationYear "2022" @default.
- W4285282124 type Work @default.
- W4285282124 citedByCount "0" @default.
- W4285282124 crossrefType "proceedings-article" @default.
- W4285282124 hasAuthorship W4285282124A5032091280 @default.
- W4285282124 hasAuthorship W4285282124A5076704114 @default.
- W4285282124 hasAuthorship W4285282124A5091677603 @default.
- W4285282124 hasBestOaLocation W42852821241 @default.
- W4285282124 hasConcept C100701293 @default.
- W4285282124 hasConcept C103278499 @default.
- W4285282124 hasConcept C115961682 @default.
- W4285282124 hasConcept C130318100 @default.
- W4285282124 hasConcept C138885662 @default.
- W4285282124 hasConcept C154945302 @default.
- W4285282124 hasConcept C15744967 @default.
- W4285282124 hasConcept C169760540 @default.
- W4285282124 hasConcept C169900460 @default.
- W4285282124 hasConcept C184337299 @default.
- W4285282124 hasConcept C199360897 @default.
- W4285282124 hasConcept C204321447 @default.
- W4285282124 hasConcept C2780876879 @default.
- W4285282124 hasConcept C41008148 @default.
- W4285282124 hasConcept C41895202 @default.
- W4285282124 hasConcept C542102704 @default.
- W4285282124 hasConcept C59822182 @default.
- W4285282124 hasConcept C81444415 @default.
- W4285282124 hasConcept C86803240 @default.
- W4285282124 hasConcept C90805587 @default.
- W4285282124 hasConceptScore W4285282124C100701293 @default.
- W4285282124 hasConceptScore W4285282124C103278499 @default.
- W4285282124 hasConceptScore W4285282124C115961682 @default.
- W4285282124 hasConceptScore W4285282124C130318100 @default.
- W4285282124 hasConceptScore W4285282124C138885662 @default.
- W4285282124 hasConceptScore W4285282124C154945302 @default.
- W4285282124 hasConceptScore W4285282124C15744967 @default.
- W4285282124 hasConceptScore W4285282124C169760540 @default.
- W4285282124 hasConceptScore W4285282124C169900460 @default.
- W4285282124 hasConceptScore W4285282124C184337299 @default.
- W4285282124 hasConceptScore W4285282124C199360897 @default.
- W4285282124 hasConceptScore W4285282124C204321447 @default.
- W4285282124 hasConceptScore W4285282124C2780876879 @default.
- W4285282124 hasConceptScore W4285282124C41008148 @default.
- W4285282124 hasConceptScore W4285282124C41895202 @default.
- W4285282124 hasConceptScore W4285282124C542102704 @default.
- W4285282124 hasConceptScore W4285282124C59822182 @default.
- W4285282124 hasConceptScore W4285282124C81444415 @default.
- W4285282124 hasConceptScore W4285282124C86803240 @default.
- W4285282124 hasConceptScore W4285282124C90805587 @default.
- W4285282124 hasLocation W42852821241 @default.
- W4285282124 hasLocation W42852821242 @default.
- W4285282124 hasOpenAccess W4285282124 @default.
- W4285282124 hasPrimaryLocation W42852821241 @default.
- W4285282124 hasRelatedWork W1996356482 @default.
- W4285282124 hasRelatedWork W2102646808 @default.
- W4285282124 hasRelatedWork W2151108588 @default.
- W4285282124 hasRelatedWork W2333425924 @default.
- W4285282124 hasRelatedWork W2559461694 @default.
- W4285282124 hasRelatedWork W2564015900 @default.
- W4285282124 hasRelatedWork W2963829519 @default.
- W4285282124 hasRelatedWork W2996282670 @default.
- W4285282124 hasRelatedWork W3214579985 @default.
- W4285282124 hasRelatedWork W4385571594 @default.
- W4285282124 isParatext "false" @default.
- W4285282124 isRetracted "false" @default.
- W4285282124 workType "article" @default.