Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994976222> ?p ?o ?g. }
- W2994976222 abstract "In many applications labeled data is not readily available, and needs to be collected via pain-staking human supervision. We propose a rule-exemplar model for collecting human supervision to combine the scalability of rules with the quality of instance labels. The supervision is coupled such that it is both natural for humans and synergistic for learning. We propose a training algorithm that jointly denoises rules via latent coverage variables, and trains the model through a soft implication loss over the coverage and label variables. Empirical evaluation on five different tasks shows that (1) our algorithm is more accurate than several existing methods of learning from a mix of clean and noisy supervision, and (2) the coupled rule-exemplar supervision is effective in denoising rules." @default.
- W2994976222 created "2019-12-26" @default.
- W2994976222 creator A5031035935 @default.
- W2994976222 creator A5047666107 @default.
- W2994976222 creator A5075255305 @default.
- W2994976222 creator A5085494874 @default.
- W2994976222 date "2020-04-30" @default.
- W2994976222 modified "2023-09-27" @default.
- W2994976222 title "Learning from Rules Generalizing Labeled Exemplars" @default.
- W2994976222 cites W1528113134 @default.
- W2994976222 cites W2012273848 @default.
- W2994976222 cites W2036166268 @default.
- W2994976222 cites W2048679005 @default.
- W2994976222 cites W2049633694 @default.
- W2994976222 cites W2070246124 @default.
- W2994976222 cites W2154368244 @default.
- W2994976222 cites W2162152253 @default.
- W2994976222 cites W2295416969 @default.
- W2994976222 cites W2577784528 @default.
- W2994976222 cites W2752971446 @default.
- W2994976222 cites W2794868398 @default.
- W2994976222 cites W2903440991 @default.
- W2994976222 cites W2923924002 @default.
- W2994976222 cites W2962756502 @default.
- W2994976222 cites W2962764460 @default.
- W2994976222 cites W2962843773 @default.
- W2994976222 cites W2963262394 @default.
- W2994976222 cites W2963341956 @default.
- W2994976222 cites W2963371670 @default.
- W2994976222 cites W2963403617 @default.
- W2994976222 cites W2963491157 @default.
- W2994976222 cites W2963644303 @default.
- W2994976222 cites W2963687836 @default.
- W2994976222 cites W2963697299 @default.
- W2994976222 cites W2963735582 @default.
- W2994976222 cites W2963737801 @default.
- W2994976222 cites W2963759070 @default.
- W2994976222 cites W2964031560 @default.
- W2994976222 cites W2964274690 @default.
- W2994976222 cites W2964289387 @default.
- W2994976222 cites W3120740533 @default.
- W2994976222 cites W4508078 @default.
- W2994976222 cites W2962915384 @default.
- W2994976222 hasPublicationYear "2020" @default.
- W2994976222 type Work @default.
- W2994976222 sameAs 2994976222 @default.
- W2994976222 citedByCount "17" @default.
- W2994976222 countsByYear W29949762222020 @default.
- W2994976222 countsByYear W29949762222021 @default.
- W2994976222 countsByYear W29949762222022 @default.
- W2994976222 crossrefType "proceedings-article" @default.
- W2994976222 hasAuthorship W2994976222A5031035935 @default.
- W2994976222 hasAuthorship W2994976222A5047666107 @default.
- W2994976222 hasAuthorship W2994976222A5075255305 @default.
- W2994976222 hasAuthorship W2994976222A5085494874 @default.
- W2994976222 hasConcept C111472728 @default.
- W2994976222 hasConcept C119857082 @default.
- W2994976222 hasConcept C124101348 @default.
- W2994976222 hasConcept C138885662 @default.
- W2994976222 hasConcept C154945302 @default.
- W2994976222 hasConcept C190839683 @default.
- W2994976222 hasConcept C205649164 @default.
- W2994976222 hasConcept C2776145971 @default.
- W2994976222 hasConcept C2779530757 @default.
- W2994976222 hasConcept C41008148 @default.
- W2994976222 hasConcept C48044578 @default.
- W2994976222 hasConcept C51167844 @default.
- W2994976222 hasConcept C58640448 @default.
- W2994976222 hasConcept C77088390 @default.
- W2994976222 hasConceptScore W2994976222C111472728 @default.
- W2994976222 hasConceptScore W2994976222C119857082 @default.
- W2994976222 hasConceptScore W2994976222C124101348 @default.
- W2994976222 hasConceptScore W2994976222C138885662 @default.
- W2994976222 hasConceptScore W2994976222C154945302 @default.
- W2994976222 hasConceptScore W2994976222C190839683 @default.
- W2994976222 hasConceptScore W2994976222C205649164 @default.
- W2994976222 hasConceptScore W2994976222C2776145971 @default.
- W2994976222 hasConceptScore W2994976222C2779530757 @default.
- W2994976222 hasConceptScore W2994976222C41008148 @default.
- W2994976222 hasConceptScore W2994976222C48044578 @default.
- W2994976222 hasConceptScore W2994976222C51167844 @default.
- W2994976222 hasConceptScore W2994976222C58640448 @default.
- W2994976222 hasConceptScore W2994976222C77088390 @default.
- W2994976222 hasLocation W29949762221 @default.
- W2994976222 hasOpenAccess W2994976222 @default.
- W2994976222 hasPrimaryLocation W29949762221 @default.
- W2994976222 hasRelatedWork W2041756589 @default.
- W2994976222 hasRelatedWork W2070246124 @default.
- W2994976222 hasRelatedWork W2113459411 @default.
- W2994976222 hasRelatedWork W2295416969 @default.
- W2994976222 hasRelatedWork W2769041395 @default.
- W2994976222 hasRelatedWork W2890931111 @default.
- W2994976222 hasRelatedWork W2895604144 @default.
- W2994976222 hasRelatedWork W2903440991 @default.
- W2994976222 hasRelatedWork W2911424454 @default.
- W2994976222 hasRelatedWork W2963012544 @default.
- W2994976222 hasRelatedWork W2963341956 @default.
- W2994976222 hasRelatedWork W2963371670 @default.
- W2994976222 hasRelatedWork W2965373594 @default.
- W2994976222 hasRelatedWork W3015342646 @default.