Matches in SemOpenAlex for { <https://semopenalex.org/work/W2923959898> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2923959898 endingPage "466" @default.
- W2923959898 startingPage "451" @default.
- W2923959898 abstract "Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word embeddings. We use a multimodal sentence encoder trained on a corpus of images with matching text captions to produce visually grounded sentence embeddings. Deep Neural Networks are trained to map the two modalities to a common embedding space such that for an image the corresponding caption can be retrieved and vice versa. We show that our model achieves results comparable to the current state-of-the-art on two popular image-caption retrieval benchmark data sets: MSCOCO and Flickr8k. We evaluate the semantic content of the resulting sentence embeddings using the data from the Semantic Textual Similarity benchmark task and show that the multimodal embeddings correlate well with human semantic similarity judgements. The system achieves state-of-the-art results on several of these benchmarks, which shows that a system trained solely on multimodal data, without assuming any word representations, is able to capture sentence level semantics. Importantly, this result shows that we do not need prior knowledge of lexical level semantics in order to model sentence level semantics. These findings demonstrate the importance of visual information in semantics." @default.
- W2923959898 created "2019-04-01" @default.
- W2923959898 creator A5031574078 @default.
- W2923959898 creator A5032091280 @default.
- W2923959898 date "2019-07-01" @default.
- W2923959898 modified "2023-09-26" @default.
- W2923959898 title "Learning semantic sentence representations from visually grounded language without lexical knowledge" @default.
- W2923959898 cites W2058354688 @default.
- W2923959898 cites W2064675550 @default.
- W2923959898 cites W2080100102 @default.
- W2923959898 cites W2164757945 @default.
- W2923959898 cites W2963849887 @default.
- W2923959898 cites W3102887392 @default.
- W2923959898 cites W3104033643 @default.
- W2923959898 cites W68733909 @default.
- W2923959898 doi "https://doi.org/10.1017/s1351324919000196" @default.
- W2923959898 hasPublicationYear "2019" @default.
- W2923959898 type Work @default.
- W2923959898 sameAs 2923959898 @default.
- W2923959898 citedByCount "7" @default.
- W2923959898 countsByYear W29239598982019 @default.
- W2923959898 countsByYear W29239598982020 @default.
- W2923959898 countsByYear W29239598982021 @default.
- W2923959898 countsByYear W29239598982022 @default.
- W2923959898 crossrefType "journal-article" @default.
- W2923959898 hasAuthorship W2923959898A5031574078 @default.
- W2923959898 hasAuthorship W2923959898A5032091280 @default.
- W2923959898 hasBestOaLocation W29239598981 @default.
- W2923959898 hasConcept C130318100 @default.
- W2923959898 hasConcept C138885662 @default.
- W2923959898 hasConcept C153083717 @default.
- W2923959898 hasConcept C154945302 @default.
- W2923959898 hasConcept C184337299 @default.
- W2923959898 hasConcept C199360897 @default.
- W2923959898 hasConcept C204321447 @default.
- W2923959898 hasConcept C2777530160 @default.
- W2923959898 hasConcept C41008148 @default.
- W2923959898 hasConcept C41895202 @default.
- W2923959898 hasConcept C90805587 @default.
- W2923959898 hasConceptScore W2923959898C130318100 @default.
- W2923959898 hasConceptScore W2923959898C138885662 @default.
- W2923959898 hasConceptScore W2923959898C153083717 @default.
- W2923959898 hasConceptScore W2923959898C154945302 @default.
- W2923959898 hasConceptScore W2923959898C184337299 @default.
- W2923959898 hasConceptScore W2923959898C199360897 @default.
- W2923959898 hasConceptScore W2923959898C204321447 @default.
- W2923959898 hasConceptScore W2923959898C2777530160 @default.
- W2923959898 hasConceptScore W2923959898C41008148 @default.
- W2923959898 hasConceptScore W2923959898C41895202 @default.
- W2923959898 hasConceptScore W2923959898C90805587 @default.
- W2923959898 hasIssue "4" @default.
- W2923959898 hasLocation W29239598981 @default.
- W2923959898 hasLocation W29239598982 @default.
- W2923959898 hasLocation W29239598983 @default.
- W2923959898 hasOpenAccess W2923959898 @default.
- W2923959898 hasPrimaryLocation W29239598981 @default.
- W2923959898 hasRelatedWork W2162130683 @default.
- W2923959898 hasRelatedWork W2289318896 @default.
- W2923959898 hasRelatedWork W2463465470 @default.
- W2923959898 hasRelatedWork W2572461156 @default.
- W2923959898 hasRelatedWork W2752567363 @default.
- W2923959898 hasRelatedWork W2946205552 @default.
- W2923959898 hasRelatedWork W2953872833 @default.
- W2923959898 hasRelatedWork W4225619937 @default.
- W2923959898 hasRelatedWork W4288350158 @default.
- W2923959898 hasRelatedWork W4299611961 @default.
- W2923959898 hasVolume "25" @default.
- W2923959898 isParatext "false" @default.
- W2923959898 isRetracted "false" @default.
- W2923959898 magId "2923959898" @default.
- W2923959898 workType "article" @default.