Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081466724> ?p ?o ?g. }
- W3081466724 endingPage "490" @default.
- W3081466724 startingPage "481" @default.
- W3081466724 abstract "Conversation generation is an important natural language processing task and has attracted much attention in recent years. The realization of the conversation model is also of great significance to the field of social computing, helping to build artificial intelligence robots on social networks. The open domain conversation model is fundamentally data-driven, which can be roughly divided into retrieval models and generation models. Although remarkable progress has been achieved in recent years, it is still difficult to get responses that are grammatically and semantically appropriate. We propose the Rerank of Retrieval-based and Transformer-based Conversation model (RRT), a novel conversation model that combines the retrieval model with the generation model for the purpose of obtaining context–appropriate response. The context–response pairs with the highest similarity from training set are retrieved using traditional retrieval method, and further ranked to obtain the retrieval candidate response. We replaced the traditional sequence-to-sequence models for conversation generation by the transformer model and achieved better results with less training time. Finally, the post-reranking module is used to rank the retrieved candidate and the generated one to obtain the final response. We conducted detailed experiments on two datasets and the results show that compared with the traditional generation model, our model has a significant improvement in each metric, and the training time is decreased by a factor of 5. Furthermore, our model is more informative and relevant to the input context than the retrieval model." @default.
- W3081466724 created "2020-09-01" @default.
- W3081466724 creator A5037443625 @default.
- W3081466724 creator A5046462412 @default.
- W3081466724 creator A5051959906 @default.
- W3081466724 creator A5053920875 @default.
- W3081466724 creator A5077894845 @default.
- W3081466724 date "2021-01-01" @default.
- W3081466724 modified "2023-09-27" @default.
- W3081466724 title "A Hybrid Chinese Conversation model based on retrieval and generation" @default.
- W3081466724 cites W2001706069 @default.
- W3081466724 cites W2083761388 @default.
- W3081466724 cites W2120615054 @default.
- W3081466724 cites W2465152470 @default.
- W3081466724 cites W2521114121 @default.
- W3081466724 cites W2561368124 @default.
- W3081466724 cites W2611614234 @default.
- W3081466724 cites W2740258984 @default.
- W3081466724 cites W2752778006 @default.
- W3081466724 cites W2792034376 @default.
- W3081466724 cites W2798456655 @default.
- W3081466724 cites W2798463315 @default.
- W3081466724 cites W2811495047 @default.
- W3081466724 cites W2886793380 @default.
- W3081466724 cites W2887202921 @default.
- W3081466724 cites W2891416139 @default.
- W3081466724 cites W2915295540 @default.
- W3081466724 cites W2921713999 @default.
- W3081466724 cites W2944474510 @default.
- W3081466724 cites W2945448489 @default.
- W3081466724 cites W2949769095 @default.
- W3081466724 cites W2951697502 @default.
- W3081466724 cites W2956655452 @default.
- W3081466724 cites W2962854379 @default.
- W3081466724 cites W2963217826 @default.
- W3081466724 cites W2963520511 @default.
- W3081466724 cites W2964232540 @default.
- W3081466724 cites W2983537304 @default.
- W3081466724 cites W2995878843 @default.
- W3081466724 cites W3022187094 @default.
- W3081466724 cites W4205671217 @default.
- W3081466724 cites W4290742115 @default.
- W3081466724 cites W839407891 @default.
- W3081466724 doi "https://doi.org/10.1016/j.future.2020.08.030" @default.
- W3081466724 hasPublicationYear "2021" @default.
- W3081466724 type Work @default.
- W3081466724 sameAs 3081466724 @default.
- W3081466724 citedByCount "5" @default.
- W3081466724 countsByYear W30814667242021 @default.
- W3081466724 countsByYear W30814667242022 @default.
- W3081466724 countsByYear W30814667242023 @default.
- W3081466724 crossrefType "journal-article" @default.
- W3081466724 hasAuthorship W3081466724A5037443625 @default.
- W3081466724 hasAuthorship W3081466724A5046462412 @default.
- W3081466724 hasAuthorship W3081466724A5051959906 @default.
- W3081466724 hasAuthorship W3081466724A5053920875 @default.
- W3081466724 hasAuthorship W3081466724A5077894845 @default.
- W3081466724 hasConcept C119857082 @default.
- W3081466724 hasConcept C121332964 @default.
- W3081466724 hasConcept C137293760 @default.
- W3081466724 hasConcept C138885662 @default.
- W3081466724 hasConcept C151730666 @default.
- W3081466724 hasConcept C154945302 @default.
- W3081466724 hasConcept C165801399 @default.
- W3081466724 hasConcept C195324797 @default.
- W3081466724 hasConcept C204321447 @default.
- W3081466724 hasConcept C23123220 @default.
- W3081466724 hasConcept C2777200299 @default.
- W3081466724 hasConcept C2779343474 @default.
- W3081466724 hasConcept C2779439875 @default.
- W3081466724 hasConcept C41008148 @default.
- W3081466724 hasConcept C41895202 @default.
- W3081466724 hasConcept C62520636 @default.
- W3081466724 hasConcept C66322947 @default.
- W3081466724 hasConcept C86803240 @default.
- W3081466724 hasConceptScore W3081466724C119857082 @default.
- W3081466724 hasConceptScore W3081466724C121332964 @default.
- W3081466724 hasConceptScore W3081466724C137293760 @default.
- W3081466724 hasConceptScore W3081466724C138885662 @default.
- W3081466724 hasConceptScore W3081466724C151730666 @default.
- W3081466724 hasConceptScore W3081466724C154945302 @default.
- W3081466724 hasConceptScore W3081466724C165801399 @default.
- W3081466724 hasConceptScore W3081466724C195324797 @default.
- W3081466724 hasConceptScore W3081466724C204321447 @default.
- W3081466724 hasConceptScore W3081466724C23123220 @default.
- W3081466724 hasConceptScore W3081466724C2777200299 @default.
- W3081466724 hasConceptScore W3081466724C2779343474 @default.
- W3081466724 hasConceptScore W3081466724C2779439875 @default.
- W3081466724 hasConceptScore W3081466724C41008148 @default.
- W3081466724 hasConceptScore W3081466724C41895202 @default.
- W3081466724 hasConceptScore W3081466724C62520636 @default.
- W3081466724 hasConceptScore W3081466724C66322947 @default.
- W3081466724 hasConceptScore W3081466724C86803240 @default.
- W3081466724 hasFunder F4320321001 @default.
- W3081466724 hasFunder F4320335726 @default.
- W3081466724 hasLocation W30814667241 @default.
- W3081466724 hasOpenAccess W3081466724 @default.
- W3081466724 hasPrimaryLocation W30814667241 @default.