Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287757663> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4287757663 abstract "The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like units and then break them down into smaller units. This suggests that the ideal way of learning a language is by starting from full semantic units. In this paper, we investigate if this is also the case for a neural model of Visually Grounded Speech trained on a speech-image retrieval task. We evaluated how well such a network is able to learn a reliable speech-to-image mapping when provided with phone, syllable, or word boundary information. We present a simple way to introduce such information into an RNN-based model and investigate which type of boundary is the most efficient. We also explore at which level of the network's architecture such information should be introduced so as to maximise its performances. Finally, we show that using multiple boundary types at once in a hierarchical structure, by which low-level segments are used to recompose high-level segments, is beneficial and yields better results than using low-level or high-level segments in isolation." @default.
- W4287757663 created "2022-07-26" @default.
- W4287757663 creator A5008481817 @default.
- W4287757663 creator A5040820339 @default.
- W4287757663 creator A5087788538 @default.
- W4287757663 date "2020-11-19" @default.
- W4287757663 modified "2023-10-01" @default.
- W4287757663 title "Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech" @default.
- W4287757663 hasPublicationYear "2020" @default.
- W4287757663 type Work @default.
- W4287757663 citedByCount "0" @default.
- W4287757663 crossrefType "proceedings-article" @default.
- W4287757663 hasAuthorship W4287757663A5008481817 @default.
- W4287757663 hasAuthorship W4287757663A5040820339 @default.
- W4287757663 hasAuthorship W4287757663A5087788538 @default.
- W4287757663 hasBestOaLocation W42877576631 @default.
- W4287757663 hasConcept C109089402 @default.
- W4287757663 hasConcept C125308379 @default.
- W4287757663 hasConcept C134306372 @default.
- W4287757663 hasConcept C137293760 @default.
- W4287757663 hasConcept C138885662 @default.
- W4287757663 hasConcept C144133560 @default.
- W4287757663 hasConcept C154945302 @default.
- W4287757663 hasConcept C162324750 @default.
- W4287757663 hasConcept C162853370 @default.
- W4287757663 hasConcept C187736073 @default.
- W4287757663 hasConcept C204321447 @default.
- W4287757663 hasConcept C2778121359 @default.
- W4287757663 hasConcept C2778707766 @default.
- W4287757663 hasConcept C2780451532 @default.
- W4287757663 hasConcept C28490314 @default.
- W4287757663 hasConcept C33923547 @default.
- W4287757663 hasConcept C41008148 @default.
- W4287757663 hasConcept C41895202 @default.
- W4287757663 hasConcept C50644808 @default.
- W4287757663 hasConcept C62354387 @default.
- W4287757663 hasConcept C89600930 @default.
- W4287757663 hasConcept C90805587 @default.
- W4287757663 hasConcept C98501671 @default.
- W4287757663 hasConceptScore W4287757663C109089402 @default.
- W4287757663 hasConceptScore W4287757663C125308379 @default.
- W4287757663 hasConceptScore W4287757663C134306372 @default.
- W4287757663 hasConceptScore W4287757663C137293760 @default.
- W4287757663 hasConceptScore W4287757663C138885662 @default.
- W4287757663 hasConceptScore W4287757663C144133560 @default.
- W4287757663 hasConceptScore W4287757663C154945302 @default.
- W4287757663 hasConceptScore W4287757663C162324750 @default.
- W4287757663 hasConceptScore W4287757663C162853370 @default.
- W4287757663 hasConceptScore W4287757663C187736073 @default.
- W4287757663 hasConceptScore W4287757663C204321447 @default.
- W4287757663 hasConceptScore W4287757663C2778121359 @default.
- W4287757663 hasConceptScore W4287757663C2778707766 @default.
- W4287757663 hasConceptScore W4287757663C2780451532 @default.
- W4287757663 hasConceptScore W4287757663C28490314 @default.
- W4287757663 hasConceptScore W4287757663C33923547 @default.
- W4287757663 hasConceptScore W4287757663C41008148 @default.
- W4287757663 hasConceptScore W4287757663C41895202 @default.
- W4287757663 hasConceptScore W4287757663C50644808 @default.
- W4287757663 hasConceptScore W4287757663C62354387 @default.
- W4287757663 hasConceptScore W4287757663C89600930 @default.
- W4287757663 hasConceptScore W4287757663C90805587 @default.
- W4287757663 hasConceptScore W4287757663C98501671 @default.
- W4287757663 hasLocation W42877576631 @default.
- W4287757663 hasLocation W42877576632 @default.
- W4287757663 hasLocation W42877576633 @default.
- W4287757663 hasLocation W42877576634 @default.
- W4287757663 hasLocation W42877576635 @default.
- W4287757663 hasOpenAccess W4287757663 @default.
- W4287757663 hasPrimaryLocation W42877576631 @default.
- W4287757663 hasRelatedWork W1536476694 @default.
- W4287757663 hasRelatedWork W2035959783 @default.
- W4287757663 hasRelatedWork W2188528341 @default.
- W4287757663 hasRelatedWork W2420187884 @default.
- W4287757663 hasRelatedWork W2578916128 @default.
- W4287757663 hasRelatedWork W2804033347 @default.
- W4287757663 hasRelatedWork W2951061418 @default.
- W4287757663 hasRelatedWork W56096989 @default.
- W4287757663 hasRelatedWork W62743518 @default.
- W4287757663 hasRelatedWork W2610894233 @default.
- W4287757663 isParatext "false" @default.
- W4287757663 isRetracted "false" @default.
- W4287757663 workType "article" @default.