Matches in SemOpenAlex for { <https://semopenalex.org/work/W2978165923> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2978165923 endingPage "617" @default.
- W2978165923 startingPage "611" @default.
- W2978165923 abstract "People learn in fast and flexible ways that have not been emulated by machines. Once a person learns a new verb he or she can effortlessly understand how to dax twice, walk and dax, or dax vigorously. There have been striking recent improvements in machine learning for natural language processing, yet the best algorithms require vast amounts of experience and struggle to generalize new concepts in compositional ways. To better understand these distinctively human abilities, we study the compositional skills of people through language-like instruction learning tasks. Our results show that people can learn and use novel functional concepts from very few examples (few-shot learning), successfully applying familiar functions to novel inputs. People can also compose concepts in complex ways that go beyond the provided demonstrations. Two additional experiments examined the assumptions and inductive biases that people make when solving these tasks, revealing three biases: mutual exclusivity, one-to-one mappings, and iconic concatenation. We discuss the implications for cognitive modeling and the potential for building machines with more human-like language learning capabilities." @default.
- W2978165923 created "2019-10-10" @default.
- W2978165923 creator A5011713946 @default.
- W2978165923 creator A5038612405 @default.
- W2978165923 creator A5081824828 @default.
- W2978165923 date "2019-01-01" @default.
- W2978165923 modified "2023-09-26" @default.
- W2978165923 title "Human few-shot learning of compositional instructions" @default.
- W2978165923 hasPublicationYear "2019" @default.
- W2978165923 type Work @default.
- W2978165923 sameAs 2978165923 @default.
- W2978165923 citedByCount "34" @default.
- W2978165923 countsByYear W29781659232019 @default.
- W2978165923 countsByYear W29781659232020 @default.
- W2978165923 countsByYear W29781659232021 @default.
- W2978165923 countsByYear W29781659232022 @default.
- W2978165923 crossrefType "journal-article" @default.
- W2978165923 hasAuthorship W2978165923A5011713946 @default.
- W2978165923 hasAuthorship W2978165923A5038612405 @default.
- W2978165923 hasAuthorship W2978165923A5081824828 @default.
- W2978165923 hasConcept C107457646 @default.
- W2978165923 hasConcept C114614502 @default.
- W2978165923 hasConcept C154945302 @default.
- W2978165923 hasConcept C15744967 @default.
- W2978165923 hasConcept C169760540 @default.
- W2978165923 hasConcept C169900460 @default.
- W2978165923 hasConcept C188147891 @default.
- W2978165923 hasConcept C195324797 @default.
- W2978165923 hasConcept C2776397901 @default.
- W2978165923 hasConcept C2779439875 @default.
- W2978165923 hasConcept C33923547 @default.
- W2978165923 hasConcept C41008148 @default.
- W2978165923 hasConcept C87619178 @default.
- W2978165923 hasConceptScore W2978165923C107457646 @default.
- W2978165923 hasConceptScore W2978165923C114614502 @default.
- W2978165923 hasConceptScore W2978165923C154945302 @default.
- W2978165923 hasConceptScore W2978165923C15744967 @default.
- W2978165923 hasConceptScore W2978165923C169760540 @default.
- W2978165923 hasConceptScore W2978165923C169900460 @default.
- W2978165923 hasConceptScore W2978165923C188147891 @default.
- W2978165923 hasConceptScore W2978165923C195324797 @default.
- W2978165923 hasConceptScore W2978165923C2776397901 @default.
- W2978165923 hasConceptScore W2978165923C2779439875 @default.
- W2978165923 hasConceptScore W2978165923C33923547 @default.
- W2978165923 hasConceptScore W2978165923C41008148 @default.
- W2978165923 hasConceptScore W2978165923C87619178 @default.
- W2978165923 hasLocation W29781659231 @default.
- W2978165923 hasOpenAccess W2978165923 @default.
- W2978165923 hasPrimaryLocation W29781659231 @default.
- W2978165923 hasRelatedWork W1496189301 @default.
- W2978165923 hasRelatedWork W2064675550 @default.
- W2978165923 hasRelatedWork W2118373646 @default.
- W2978165923 hasRelatedWork W2130942839 @default.
- W2978165923 hasRelatedWork W2561715562 @default.
- W2978165923 hasRelatedWork W2781474777 @default.
- W2978165923 hasRelatedWork W2887970879 @default.
- W2978165923 hasRelatedWork W2939413764 @default.
- W2978165923 hasRelatedWork W2962968135 @default.
- W2978165923 hasRelatedWork W2963267799 @default.
- W2978165923 hasRelatedWork W2963305465 @default.
- W2978165923 hasRelatedWork W2963341956 @default.
- W2978165923 hasRelatedWork W2963403868 @default.
- W2978165923 hasRelatedWork W2963655793 @default.
- W2978165923 hasRelatedWork W2964121744 @default.
- W2978165923 hasRelatedWork W2964308564 @default.
- W2978165923 hasRelatedWork W2990379018 @default.
- W2978165923 hasRelatedWork W2996094825 @default.
- W2978165923 hasRelatedWork W2996346899 @default.
- W2978165923 hasRelatedWork W3035331128 @default.
- W2978165923 isParatext "false" @default.
- W2978165923 isRetracted "false" @default.
- W2978165923 magId "2978165923" @default.
- W2978165923 workType "article" @default.