Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200526120> ?p ?o ?g. }
- W3200526120 abstract "The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible with a large amount of parallel data, it is often impossible to collect such data for different styles. In this paper, instead of manually constructing conversation data with a certain style, we propose a flexible framework that adapts a generic retrieval-based dialogue system to mimic the language style of a specified persona without any parallel data. Our approach is based on automatic generation of stylized data by learning the usage of jargon, and then rewriting the generic conversations to a stylized one by incorporating the jargon. In experiments we implemented dialogue systems with five distinct language styles, and the result shows our framework significantly outperforms baselines in terms of the average score of responses' relevance and style degree, and content diversity. A/B testing on a commercial chatbot shows that users are more satisfied with our system. This study demonstrates the feasibility of building stylistic dialogue systems by simple data augmentation." @default.
- W3200526120 created "2021-09-27" @default.
- W3200526120 creator A5003642180 @default.
- W3200526120 creator A5014720604 @default.
- W3200526120 creator A5015800533 @default.
- W3200526120 creator A5018977183 @default.
- W3200526120 creator A5031351839 @default.
- W3200526120 date "2021-09-12" @default.
- W3200526120 modified "2023-10-17" @default.
- W3200526120 title "Stylistic Retrieval-based Dialogue System with Unparallel Training Data" @default.
- W3200526120 cites W2339852062 @default.
- W3200526120 cites W2493916176 @default.
- W3200526120 cites W2578354947 @default.
- W3200526120 cites W2741352528 @default.
- W3200526120 cites W2786913767 @default.
- W3200526120 cites W2798456655 @default.
- W3200526120 cites W2801454967 @default.
- W3200526120 cites W2822830299 @default.
- W3200526120 cites W2891416139 @default.
- W3200526120 cites W2896457183 @default.
- W3200526120 cites W2908331278 @default.
- W3200526120 cites W2962686347 @default.
- W3200526120 cites W2962753250 @default.
- W3200526120 cites W2962796276 @default.
- W3200526120 cites W2962912551 @default.
- W3200526120 cites W2962917899 @default.
- W3200526120 cites W2963034998 @default.
- W3200526120 cites W2963206148 @default.
- W3200526120 cites W2963366196 @default.
- W3200526120 cites W2963667126 @default.
- W3200526120 cites W2963825865 @default.
- W3200526120 cites W2963963856 @default.
- W3200526120 cites W2963995063 @default.
- W3200526120 cites W2964008635 @default.
- W3200526120 cites W2964222296 @default.
- W3200526120 cites W2964309167 @default.
- W3200526120 cites W2964529779 @default.
- W3200526120 cites W2970562804 @default.
- W3200526120 cites W2977188956 @default.
- W3200526120 cites W2985412081 @default.
- W3200526120 cites W3014299638 @default.
- W3200526120 cites W3014508569 @default.
- W3200526120 cites W3016829315 @default.
- W3200526120 cites W3088677288 @default.
- W3200526120 cites W3100727892 @default.
- W3200526120 cites W3104616748 @default.
- W3200526120 cites W3166046446 @default.
- W3200526120 cites W3168988646 @default.
- W3200526120 cites W3169461319 @default.
- W3200526120 cites W3172152151 @default.
- W3200526120 cites W3176015769 @default.
- W3200526120 cites W613277099 @default.
- W3200526120 doi "https://doi.org/10.48550/arxiv.2109.05477" @default.
- W3200526120 hasPublicationYear "2021" @default.
- W3200526120 type Work @default.
- W3200526120 sameAs 3200526120 @default.
- W3200526120 citedByCount "0" @default.
- W3200526120 crossrefType "posted-content" @default.
- W3200526120 hasAuthorship W3200526120A5003642180 @default.
- W3200526120 hasAuthorship W3200526120A5014720604 @default.
- W3200526120 hasAuthorship W3200526120A5015800533 @default.
- W3200526120 hasAuthorship W3200526120A5018977183 @default.
- W3200526120 hasAuthorship W3200526120A5031351839 @default.
- W3200526120 hasBestOaLocation W32005261201 @default.
- W3200526120 hasConcept C107457646 @default.
- W3200526120 hasConcept C136764020 @default.
- W3200526120 hasConcept C138885662 @default.
- W3200526120 hasConcept C139719470 @default.
- W3200526120 hasConcept C154945302 @default.
- W3200526120 hasConcept C158154518 @default.
- W3200526120 hasConcept C162324750 @default.
- W3200526120 hasConcept C166957645 @default.
- W3200526120 hasConcept C170130773 @default.
- W3200526120 hasConcept C173853756 @default.
- W3200526120 hasConcept C17744445 @default.
- W3200526120 hasConcept C183003079 @default.
- W3200526120 hasConcept C190954187 @default.
- W3200526120 hasConcept C199539241 @default.
- W3200526120 hasConcept C204321447 @default.
- W3200526120 hasConcept C23123220 @default.
- W3200526120 hasConcept C2776445246 @default.
- W3200526120 hasConcept C2777611551 @default.
- W3200526120 hasConcept C2779041454 @default.
- W3200526120 hasConcept C38935604 @default.
- W3200526120 hasConcept C41008148 @default.
- W3200526120 hasConcept C41895202 @default.
- W3200526120 hasConcept C95457728 @default.
- W3200526120 hasConceptScore W3200526120C107457646 @default.
- W3200526120 hasConceptScore W3200526120C136764020 @default.
- W3200526120 hasConceptScore W3200526120C138885662 @default.
- W3200526120 hasConceptScore W3200526120C139719470 @default.
- W3200526120 hasConceptScore W3200526120C154945302 @default.
- W3200526120 hasConceptScore W3200526120C158154518 @default.
- W3200526120 hasConceptScore W3200526120C162324750 @default.
- W3200526120 hasConceptScore W3200526120C166957645 @default.
- W3200526120 hasConceptScore W3200526120C170130773 @default.
- W3200526120 hasConceptScore W3200526120C173853756 @default.
- W3200526120 hasConceptScore W3200526120C17744445 @default.
- W3200526120 hasConceptScore W3200526120C183003079 @default.
- W3200526120 hasConceptScore W3200526120C190954187 @default.