FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951287343> ?p ?o ?g. }

• W2951287343 abstract "We study learning of a matching model for response selection in retrieval-based dialogue systems. The problem is equally important with designing the architecture of a model, but is less explored in existing literature. To learn a robust matching model from noisy training data, we propose a general co-teaching framework with three specific teaching strategies that cover both teaching with loss functions and teaching with data curriculum. Under the framework, we simultaneously learn two matching models with independent training sets. In each iteration, one model transfers the knowledge learned from its training set to the other model, and at the same time receives the guide from the other model on how to overcome noise in training. Through being both a teacher and a student, the two models learn from each other and get improved together. Evaluation results on two public data sets indicate that the proposed learning approach can generally and significantly improve the performance of existing matching models." @default.
• W2951287343 created "2019-06-27" @default.
• W2951287343 creator A5013569210 @default.
• W2951287343 creator A5036495504 @default.
• W2951287343 creator A5037132097 @default.
• W2951287343 creator A5057256093 @default.
• W2951287343 creator A5058189738 @default.
• W2951287343 creator A5073065834 @default.
• W2951287343 date "2019-01-01" @default.
• W2951287343 modified "2023-10-16" @default.
• W2951287343 title "Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems" @default.
• W2951287343 cites W1527783480 @default.
• W2951287343 cites W1591706642 @default.
• W2951287343 cites W1975879668 @default.
• W2951287343 cites W2100913937 @default.
• W2951287343 cites W2102531443 @default.
• W2951287343 cites W2128892113 @default.
• W2951287343 cites W2153579005 @default.
• W2951287343 cites W2170738476 @default.
• W2951287343 cites W2256388387 @default.
• W2951287343 cites W2296073425 @default.
• W2951287343 cites W2339852062 @default.
• W2951287343 cites W2561368124 @default.
• W2951287343 cites W2786471719 @default.
• W2951287343 cites W2798033004 @default.
• W2951287343 cites W2798456655 @default.
• W2951287343 cites W2807880213 @default.
• W2951287343 cites W2809210859 @default.
• W2951287343 cites W2891416139 @default.
• W2951287343 cites W295828404 @default.
• W2951287343 cites W2962707484 @default.
• W2951287343 cites W2962768358 @default.
• W2951287343 cites W2962796276 @default.
• W2951287343 cites W2962838727 @default.
• W2951287343 cites W2962854379 @default.
• W2951287343 cites W2963035145 @default.
• W2951287343 cites W2963386594 @default.
• W2951287343 cites W2963780286 @default.
• W2951287343 cites W2963826056 @default.
• W2951287343 cites W2963962154 @default.
• W2951287343 cites W2963963856 @default.
• W2951287343 cites W2963986868 @default.
• W2951287343 cites W2964092386 @default.
• W2951287343 cites W2964121744 @default.
• W2951287343 cites W2964309167 @default.
• W2951287343 cites W2964352131 @default.
• W2951287343 doi "https://doi.org/10.18653/v1/p19-1370" @default.
• W2951287343 hasPublicationYear "2019" @default.
• W2951287343 type Work @default.
• W2951287343 sameAs 2951287343 @default.
• W2951287343 citedByCount "22" @default.
• W2951287343 countsByYear W29512873432020 @default.
• W2951287343 countsByYear W29512873432021 @default.
• W2951287343 countsByYear W29512873432022 @default.
• W2951287343 crossrefType "proceedings-article" @default.
• W2951287343 hasAuthorship W2951287343A5013569210 @default.
• W2951287343 hasAuthorship W2951287343A5036495504 @default.
• W2951287343 hasAuthorship W2951287343A5037132097 @default.
• W2951287343 hasAuthorship W2951287343A5057256093 @default.
• W2951287343 hasAuthorship W2951287343A5058189738 @default.
• W2951287343 hasAuthorship W2951287343A5073065834 @default.
• W2951287343 hasBestOaLocation W29512873432 @default.
• W2951287343 hasConcept C105795698 @default.
• W2951287343 hasConcept C119857082 @default.
• W2951287343 hasConcept C123657996 @default.
• W2951287343 hasConcept C127413603 @default.
• W2951287343 hasConcept C142362112 @default.
• W2951287343 hasConcept C153349607 @default.
• W2951287343 hasConcept C154945302 @default.
• W2951287343 hasConcept C15744967 @default.
• W2951287343 hasConcept C165064840 @default.
• W2951287343 hasConcept C177264268 @default.
• W2951287343 hasConcept C19417346 @default.
• W2951287343 hasConcept C199360897 @default.
• W2951287343 hasConcept C2780428219 @default.
• W2951287343 hasConcept C33923547 @default.
• W2951287343 hasConcept C41008148 @default.
• W2951287343 hasConcept C47177190 @default.
• W2951287343 hasConcept C51632099 @default.
• W2951287343 hasConcept C78519656 @default.
• W2951287343 hasConcept C81917197 @default.
• W2951287343 hasConcept C93959086 @default.
• W2951287343 hasConceptScore W2951287343C105795698 @default.
• W2951287343 hasConceptScore W2951287343C119857082 @default.
• W2951287343 hasConceptScore W2951287343C123657996 @default.
• W2951287343 hasConceptScore W2951287343C127413603 @default.
• W2951287343 hasConceptScore W2951287343C142362112 @default.
• W2951287343 hasConceptScore W2951287343C153349607 @default.
• W2951287343 hasConceptScore W2951287343C154945302 @default.
• W2951287343 hasConceptScore W2951287343C15744967 @default.
• W2951287343 hasConceptScore W2951287343C165064840 @default.
• W2951287343 hasConceptScore W2951287343C177264268 @default.
• W2951287343 hasConceptScore W2951287343C19417346 @default.
• W2951287343 hasConceptScore W2951287343C199360897 @default.
• W2951287343 hasConceptScore W2951287343C2780428219 @default.
• W2951287343 hasConceptScore W2951287343C33923547 @default.
• W2951287343 hasConceptScore W2951287343C41008148 @default.
• W2951287343 hasConceptScore W2951287343C47177190 @default.
• W2951287343 hasConceptScore W2951287343C51632099 @default.
• W2951287343 hasConceptScore W2951287343C78519656 @default.

• next