FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295290471> ?p ?o ?g. }

• W4295290471 abstract "With the resurgent interest in building open-domain dialogue systems, the dialogue generation task has attracted increasing attention over the past few years. This task is usually formulated as a conditional generation problem, which aims to generate a natural and meaningful response given dialogue contexts and specific constraints, such as persona. And maintaining a consistent persona is essential for the dialogue systems to gain trust from the users. Although tremendous advancements have been brought, traditional persona-based dialogue models are typically trained by leveraging a large number of persona-dense dialogue examples. Yet, such persona-dense training data are expensive to obtain, leading to a limited scale. This work presents a novel approach to learning from limited training examples by regarding consistency understanding as a regularization of response generation. To this end, we propose a novel stack-propagation framework for learning a generation and understanding pipeline. Specifically, the framework stacks a Transformer encoder and two Transformer decoders, where the first decoder models response generation and the second serves as a regularizer and jointly models response generation and consistency understanding. The proposed framework can benefit from the stacked encoder and decoders to learn from much smaller personalized dialogue data while maintaining competitive performance. Under different low-resource settings, subjective and objective evaluations prove that the stack-propagation framework outperforms strong baselines in response quality and persona consistency and largely overcomes the shortcomings of traditional models that rely heavily on the persona-dense dialogue data." @default.
• W4295290471 created "2022-09-12" @default.
• W4295290471 creator A5044420239 @default.
• W4295290471 creator A5063089557 @default.
• W4295290471 creator A5087762339 @default.
• W4295290471 creator A5090720315 @default.
• W4295290471 date "2022-09-12" @default.
• W4295290471 modified "2023-10-11" @default.
• W4295290471 title "A Stack-Propagation Framework for Low-Resource Personalized Dialogue Generation" @default.
• W4295290471 cites W1518951372 @default.
• W4295290471 cites W1840435438 @default.
• W4295290471 cites W1974770283 @default.
• W4295290471 cites W2001771035 @default.
• W4295290471 cites W2139575250 @default.
• W4295290471 cites W2311095070 @default.
• W4295290471 cites W2339852062 @default.
• W4295290471 cites W2521114121 @default.
• W4295290471 cites W2578354947 @default.
• W4295290471 cites W2740309605 @default.
• W4295290471 cites W2741363662 @default.
• W4295290471 cites W2798456655 @default.
• W4295290471 cites W2891416139 @default.
• W4295290471 cites W2945978556 @default.
• W4295290471 cites W2952638691 @default.
• W4295290471 cites W2953039584 @default.
• W4295290471 cites W2962796276 @default.
• W4295290471 cites W2962989446 @default.
• W4295290471 cites W2963064439 @default.
• W4295290471 cites W2963167310 @default.
• W4295290471 cites W2963206148 @default.
• W4295290471 cites W2963521540 @default.
• W4295290471 cites W2963544700 @default.
• W4295290471 cites W2963640662 @default.
• W4295290471 cites W2963825865 @default.
• W4295290471 cites W2963846996 @default.
• W4295290471 cites W2964165364 @default.
• W4295290471 cites W2964238590 @default.
• W4295290471 cites W2964352131 @default.
• W4295290471 cites W2965718149 @default.
• W4295290471 cites W2997892440 @default.
• W4295290471 cites W3015322406 @default.
• W4295290471 cites W3025611493 @default.
• W4295290471 cites W3033557797 @default.
• W4295290471 cites W3034600233 @default.
• W4295290471 cites W3034720580 @default.
• W4295290471 cites W3034999214 @default.
• W4295290471 cites W3035044096 @default.
• W4295290471 cites W3035068109 @default.
• W4295290471 cites W3035451444 @default.
• W4295290471 cites W3082549344 @default.
• W4295290471 cites W3087232873 @default.
• W4295290471 cites W3114651185 @default.
• W4295290471 cites W3155584966 @default.
• W4295290471 cites W3168988646 @default.
• W4295290471 cites W3193685260 @default.
• W4295290471 cites W4251326898 @default.
• W4295290471 doi "https://doi.org/10.1145/3563389" @default.
• W4295290471 hasPublicationYear "2022" @default.
• W4295290471 type Work @default.
• W4295290471 citedByCount "1" @default.
• W4295290471 countsByYear W42952904712023 @default.
• W4295290471 crossrefType "journal-article" @default.
• W4295290471 hasAuthorship W4295290471A5044420239 @default.
• W4295290471 hasAuthorship W4295290471A5063089557 @default.
• W4295290471 hasAuthorship W4295290471A5087762339 @default.
• W4295290471 hasAuthorship W4295290471A5090720315 @default.
• W4295290471 hasBestOaLocation W42952904711 @default.
• W4295290471 hasConcept C107457646 @default.
• W4295290471 hasConcept C111919701 @default.
• W4295290471 hasConcept C118505674 @default.
• W4295290471 hasConcept C119857082 @default.
• W4295290471 hasConcept C121332964 @default.
• W4295290471 hasConcept C154945302 @default.
• W4295290471 hasConcept C165801399 @default.
• W4295290471 hasConcept C204321447 @default.
• W4295290471 hasConcept C2522767166 @default.
• W4295290471 hasConcept C2776436953 @default.
• W4295290471 hasConcept C313442 @default.
• W4295290471 hasConcept C41008148 @default.
• W4295290471 hasConcept C62520636 @default.
• W4295290471 hasConcept C66322947 @default.
• W4295290471 hasConceptScore W4295290471C107457646 @default.
• W4295290471 hasConceptScore W4295290471C111919701 @default.
• W4295290471 hasConceptScore W4295290471C118505674 @default.
• W4295290471 hasConceptScore W4295290471C119857082 @default.
• W4295290471 hasConceptScore W4295290471C121332964 @default.
• W4295290471 hasConceptScore W4295290471C154945302 @default.
• W4295290471 hasConceptScore W4295290471C165801399 @default.
• W4295290471 hasConceptScore W4295290471C204321447 @default.
• W4295290471 hasConceptScore W4295290471C2522767166 @default.
• W4295290471 hasConceptScore W4295290471C2776436953 @default.
• W4295290471 hasConceptScore W4295290471C313442 @default.
• W4295290471 hasConceptScore W4295290471C41008148 @default.
• W4295290471 hasConceptScore W4295290471C62520636 @default.
• W4295290471 hasConceptScore W4295290471C66322947 @default.
• W4295290471 hasLocation W42952904711 @default.
• W4295290471 hasOpenAccess W4295290471 @default.
• W4295290471 hasPrimaryLocation W42952904711 @default.
• W4295290471 hasRelatedWork W2909970382 @default.
• W4295290471 hasRelatedWork W3023944410 @default.

• next