Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283215748> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4283215748 abstract "Language grounding to vision is an active field of research aiming to enrich text-based representations of word meanings by leveraging perceptual knowledge from vision. Despite many attempts at language grounding, it is still unclear how to effectively inject visual knowledge into the word embeddings of a language in such a way that a proper balance of textual and visual knowledge is maintained. Some common concerns are the following. Is visual grounding beneficial for abstract words or is its contribution only limited to concrete words? What is the optimal way of bridging the gap between text and vision? How much do we gain by visually grounding textual embeddings? The present study addresses these questions by proposing a simple yet very effective grounding approach for pre-trained word embeddings. Our model aligns textual embeddings with vision while largely preserving the distributional statistics that characterize word use in text corpora. By applying a learned alignment, we are able to generate visually grounded embeddings for unseen words, including abstract words. A series of evaluations on word similarity benchmarks shows that visual grounding is beneficial not only for concrete words, but also for abstract words. We also show that our method for visual grounding offers advantages for contextualized embeddings, but only when these are trained on corpora of relatively modest size. Code and grounded embeddings for English are available at https://github.com/Hazel1994/Visually_Grounded_Word_Embeddings_2." @default.
- W4283215748 created "2022-06-22" @default.
- W4283215748 creator A5002918682 @default.
- W4283215748 creator A5005750986 @default.
- W4283215748 creator A5026215663 @default.
- W4283215748 creator A5036948222 @default.
- W4283215748 creator A5087366961 @default.
- W4283215748 date "2022-06-17" @default.
- W4283215748 modified "2023-09-30" @default.
- W4283215748 title "Language with Vision: a Study on Grounded Word and Sentence Embeddings" @default.
- W4283215748 doi "https://doi.org/10.48550/arxiv.2206.08823" @default.
- W4283215748 hasPublicationYear "2022" @default.
- W4283215748 type Work @default.
- W4283215748 citedByCount "0" @default.
- W4283215748 crossrefType "posted-content" @default.
- W4283215748 hasAuthorship W4283215748A5002918682 @default.
- W4283215748 hasAuthorship W4283215748A5005750986 @default.
- W4283215748 hasAuthorship W4283215748A5026215663 @default.
- W4283215748 hasAuthorship W4283215748A5036948222 @default.
- W4283215748 hasAuthorship W4283215748A5087366961 @default.
- W4283215748 hasBestOaLocation W42832157481 @default.
- W4283215748 hasConcept C138885662 @default.
- W4283215748 hasConcept C154945302 @default.
- W4283215748 hasConcept C15744967 @default.
- W4283215748 hasConcept C169760540 @default.
- W4283215748 hasConcept C204321447 @default.
- W4283215748 hasConcept C26760741 @default.
- W4283215748 hasConcept C2777530160 @default.
- W4283215748 hasConcept C41008148 @default.
- W4283215748 hasConcept C41895202 @default.
- W4283215748 hasConcept C90805587 @default.
- W4283215748 hasConceptScore W4283215748C138885662 @default.
- W4283215748 hasConceptScore W4283215748C154945302 @default.
- W4283215748 hasConceptScore W4283215748C15744967 @default.
- W4283215748 hasConceptScore W4283215748C169760540 @default.
- W4283215748 hasConceptScore W4283215748C204321447 @default.
- W4283215748 hasConceptScore W4283215748C26760741 @default.
- W4283215748 hasConceptScore W4283215748C2777530160 @default.
- W4283215748 hasConceptScore W4283215748C41008148 @default.
- W4283215748 hasConceptScore W4283215748C41895202 @default.
- W4283215748 hasConceptScore W4283215748C90805587 @default.
- W4283215748 hasLocation W42832157481 @default.
- W4283215748 hasOpenAccess W4283215748 @default.
- W4283215748 hasPrimaryLocation W42832157481 @default.
- W4283215748 hasRelatedWork W1508636238 @default.
- W4283215748 hasRelatedWork W1517743118 @default.
- W4283215748 hasRelatedWork W1519302135 @default.
- W4283215748 hasRelatedWork W1567338489 @default.
- W4283215748 hasRelatedWork W159132833 @default.
- W4283215748 hasRelatedWork W1978971213 @default.
- W4283215748 hasRelatedWork W1986021162 @default.
- W4283215748 hasRelatedWork W2125145484 @default.
- W4283215748 hasRelatedWork W2398825887 @default.
- W4283215748 hasRelatedWork W38394648 @default.
- W4283215748 isParatext "false" @default.
- W4283215748 isRetracted "false" @default.
- W4283215748 workType "article" @default.