Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313854628> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4313854628 abstract "Multi-turn dialogue is the major manifestation of a conversation. Compared with single-turn dialogue, response selection is more complex as the context varies. We stress the importance of dialogue history and apply the pre-trained model BERT to assign proper weight to each utterance of a dialogue. Previous works take all the dialogue history as context to measure the matching degree of a context-response pair, causing the quadratic computational cost and truncation of longer sequences exceeding the length limitation of BERT. We propose a sentence-based method to deal with the aforementioned problems, obtaining the sentence embedding of a single unit utterance of dialogue and forming a classification token of a context-response pair. We discuss how to obtain a sentence embedding with high quality and to design the input representations in response selection. The results show that the average of the first-last layer output exhibits the best performance for obtaining a sentence representation. The proposed method, concatenating the sentence embeddings of context with the token embeddings of response candidates, is nearly on a par with the token embedding based SOTA method. Notably, the processable length of dialogue history is enlarged about ten times with a low computational cost, potentially reducing chatbot response time and inspiring user engagement." @default.
- W4313854628 created "2023-01-10" @default.
- W4313854628 creator A5000452220 @default.
- W4313854628 creator A5004592091 @default.
- W4313854628 creator A5077435054 @default.
- W4313854628 date "2022-11-27" @default.
- W4313854628 modified "2023-10-14" @default.
- W4313854628 title "Leveraging Extended Chat History through Sentence Embedding in Multi-turn Dialogue toward Increasing User Engagement" @default.
- W4313854628 doi "https://doi.org/10.23919/iccas55662.2022.10003889" @default.
- W4313854628 hasPublicationYear "2022" @default.
- W4313854628 type Work @default.
- W4313854628 citedByCount "0" @default.
- W4313854628 crossrefType "proceedings-article" @default.
- W4313854628 hasAuthorship W4313854628A5000452220 @default.
- W4313854628 hasAuthorship W4313854628A5004592091 @default.
- W4313854628 hasAuthorship W4313854628A5077435054 @default.
- W4313854628 hasConcept C105795698 @default.
- W4313854628 hasConcept C151730666 @default.
- W4313854628 hasConcept C154945302 @default.
- W4313854628 hasConcept C15744967 @default.
- W4313854628 hasConcept C165064840 @default.
- W4313854628 hasConcept C204321447 @default.
- W4313854628 hasConcept C2775852435 @default.
- W4313854628 hasConcept C2777200299 @default.
- W4313854628 hasConcept C2777530160 @default.
- W4313854628 hasConcept C2779343474 @default.
- W4313854628 hasConcept C28490314 @default.
- W4313854628 hasConcept C33923547 @default.
- W4313854628 hasConcept C38652104 @default.
- W4313854628 hasConcept C41008148 @default.
- W4313854628 hasConcept C41608201 @default.
- W4313854628 hasConcept C46312422 @default.
- W4313854628 hasConcept C48145219 @default.
- W4313854628 hasConcept C81917197 @default.
- W4313854628 hasConcept C86803240 @default.
- W4313854628 hasConceptScore W4313854628C105795698 @default.
- W4313854628 hasConceptScore W4313854628C151730666 @default.
- W4313854628 hasConceptScore W4313854628C154945302 @default.
- W4313854628 hasConceptScore W4313854628C15744967 @default.
- W4313854628 hasConceptScore W4313854628C165064840 @default.
- W4313854628 hasConceptScore W4313854628C204321447 @default.
- W4313854628 hasConceptScore W4313854628C2775852435 @default.
- W4313854628 hasConceptScore W4313854628C2777200299 @default.
- W4313854628 hasConceptScore W4313854628C2777530160 @default.
- W4313854628 hasConceptScore W4313854628C2779343474 @default.
- W4313854628 hasConceptScore W4313854628C28490314 @default.
- W4313854628 hasConceptScore W4313854628C33923547 @default.
- W4313854628 hasConceptScore W4313854628C38652104 @default.
- W4313854628 hasConceptScore W4313854628C41008148 @default.
- W4313854628 hasConceptScore W4313854628C41608201 @default.
- W4313854628 hasConceptScore W4313854628C46312422 @default.
- W4313854628 hasConceptScore W4313854628C48145219 @default.
- W4313854628 hasConceptScore W4313854628C81917197 @default.
- W4313854628 hasConceptScore W4313854628C86803240 @default.
- W4313854628 hasLocation W43138546281 @default.
- W4313854628 hasOpenAccess W4313854628 @default.
- W4313854628 hasPrimaryLocation W43138546281 @default.
- W4313854628 hasRelatedWork W1566274093 @default.
- W4313854628 hasRelatedWork W2093212730 @default.
- W4313854628 hasRelatedWork W2171511892 @default.
- W4313854628 hasRelatedWork W2351961066 @default.
- W4313854628 hasRelatedWork W2822830299 @default.
- W4313854628 hasRelatedWork W2949446780 @default.
- W4313854628 hasRelatedWork W2949747155 @default.
- W4313854628 hasRelatedWork W2962898344 @default.
- W4313854628 hasRelatedWork W2970688662 @default.
- W4313854628 hasRelatedWork W3107474891 @default.
- W4313854628 isParatext "false" @default.
- W4313854628 isRetracted "false" @default.
- W4313854628 workType "article" @default.