Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951194225> ?p ?o ?g. }
- W2951194225 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.
- W2951194225 created "2019-06-27" @default.
- W2951194225 creator A5013569210 @default.
- W2951194225 creator A5036495504 @default.
- W2951194225 creator A5037132097 @default.
- W2951194225 creator A5057256093 @default.
- W2951194225 creator A5058189738 @default.
- W2951194225 creator A5073065834 @default.
- W2951194225 date "2019-06-11" @default.
- W2951194225 modified "2023-10-16" @default.
- W2951194225 title "Learning a Matching Model with Co-teaching for Multi-turn Response Selection in Retrieval-based Dialogue Systems" @default.
- W2951194225 cites W1527783480 @default.
- W2951194225 cites W1591706642 @default.
- W2951194225 cites W1910529161 @default.
- W2951194225 cites W1975879668 @default.
- W2951194225 cites W2100913937 @default.
- W2951194225 cites W2102531443 @default.
- W2951194225 cites W2128892113 @default.
- W2951194225 cites W2153579005 @default.
- W2951194225 cites W2170738476 @default.
- W2951194225 cites W2256388387 @default.
- W2951194225 cites W2296073425 @default.
- W2951194225 cites W2339852062 @default.
- W2951194225 cites W2365750411 @default.
- W2951194225 cites W2561368124 @default.
- W2951194225 cites W2784400615 @default.
- W2951194225 cites W2786471719 @default.
- W2951194225 cites W2798033004 @default.
- W2951194225 cites W2798456655 @default.
- W2951194225 cites W2807880213 @default.
- W2951194225 cites W2809210859 @default.
- W2951194225 cites W2891416139 @default.
- W2951194225 cites W2897444426 @default.
- W2951194225 cites W295828404 @default.
- W2951194225 cites W2962707484 @default.
- W2951194225 cites W2962796276 @default.
- W2951194225 cites W2962838727 @default.
- W2951194225 cites W2962854379 @default.
- W2951194225 cites W2963035145 @default.
- W2951194225 cites W2963386594 @default.
- W2951194225 cites W2963780286 @default.
- W2951194225 cites W2963826056 @default.
- W2951194225 cites W2963963856 @default.
- W2951194225 cites W2963986868 @default.
- W2951194225 cites W2964092386 @default.
- W2951194225 cites W2964121744 @default.
- W2951194225 cites W2964309167 @default.
- W2951194225 cites W2964352131 @default.
- W2951194225 doi "https://doi.org/10.48550/arxiv.1906.04413" @default.
- W2951194225 hasPublicationYear "2019" @default.
- W2951194225 type Work @default.
- W2951194225 sameAs 2951194225 @default.
- W2951194225 citedByCount "3" @default.
- W2951194225 countsByYear W29511942252020 @default.
- W2951194225 crossrefType "posted-content" @default.
- W2951194225 hasAuthorship W2951194225A5013569210 @default.
- W2951194225 hasAuthorship W2951194225A5036495504 @default.
- W2951194225 hasAuthorship W2951194225A5037132097 @default.
- W2951194225 hasAuthorship W2951194225A5057256093 @default.
- W2951194225 hasAuthorship W2951194225A5058189738 @default.
- W2951194225 hasAuthorship W2951194225A5073065834 @default.
- W2951194225 hasBestOaLocation W29511942251 @default.
- W2951194225 hasConcept C105795698 @default.
- W2951194225 hasConcept C119857082 @default.
- W2951194225 hasConcept C123657996 @default.
- W2951194225 hasConcept C142362112 @default.
- W2951194225 hasConcept C153349607 @default.
- W2951194225 hasConcept C154945302 @default.
- W2951194225 hasConcept C15744967 @default.
- W2951194225 hasConcept C165064840 @default.
- W2951194225 hasConcept C177264268 @default.
- W2951194225 hasConcept C19417346 @default.
- W2951194225 hasConcept C199360897 @default.
- W2951194225 hasConcept C33923547 @default.
- W2951194225 hasConcept C41008148 @default.
- W2951194225 hasConcept C47177190 @default.
- W2951194225 hasConcept C51632099 @default.
- W2951194225 hasConcept C81917197 @default.
- W2951194225 hasConcept C93959086 @default.
- W2951194225 hasConceptScore W2951194225C105795698 @default.
- W2951194225 hasConceptScore W2951194225C119857082 @default.
- W2951194225 hasConceptScore W2951194225C123657996 @default.
- W2951194225 hasConceptScore W2951194225C142362112 @default.
- W2951194225 hasConceptScore W2951194225C153349607 @default.
- W2951194225 hasConceptScore W2951194225C154945302 @default.
- W2951194225 hasConceptScore W2951194225C15744967 @default.
- W2951194225 hasConceptScore W2951194225C165064840 @default.
- W2951194225 hasConceptScore W2951194225C177264268 @default.
- W2951194225 hasConceptScore W2951194225C19417346 @default.
- W2951194225 hasConceptScore W2951194225C199360897 @default.
- W2951194225 hasConceptScore W2951194225C33923547 @default.
- W2951194225 hasConceptScore W2951194225C41008148 @default.
- W2951194225 hasConceptScore W2951194225C47177190 @default.
- W2951194225 hasConceptScore W2951194225C51632099 @default.
- W2951194225 hasConceptScore W2951194225C81917197 @default.
- W2951194225 hasConceptScore W2951194225C93959086 @default.
- W2951194225 hasLocation W29511942251 @default.
- W2951194225 hasOpenAccess W2951194225 @default.
- W2951194225 hasPrimaryLocation W29511942251 @default.
- W2951194225 hasRelatedWork W2031164495 @default.