Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113287731> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3113287731 abstract "We study the coarse-grained selection module in retrieval-based chatbot. Coarse-grained selection is a basic module in a retrieval-based chatbot, which constructs a rough candidate set from the whole database to speed up the interaction with customers. So far, there are two kinds of approaches for coarse-grained selection module: (1) sparse representation; (2) dense representation. To the best of our knowledge, there is no systematic comparison between these two approaches in retrieval-based chatbots, and which kind of method is better in real scenarios is still an open question. In this paper, we first systematically compare these two methods from four aspects: (1) effectiveness; (2) index stoarge; (3) search time cost; (4) human evaluation. Extensive experiment results demonstrate that dense representation method significantly outperforms the sparse representation, but costs more time and storage occupation. In order to overcome these fatal weaknesses of dense representation method, we propose an ultra-fast, low-storage, and highly effective Deep Semantic Hashing Coarse-grained selection method, called DSHC model. Specifically, in our proposed DSHC model, a hashing optimizing module that consists of two autoencoder models is stacked on a trained dense representation model, and three loss functions are designed to optimize it. The hash codes provided by hashing optimizing module effectively preserve the rich semantic and similarity information in dense vectors. Extensive experiment results prove that, our proposed DSHC model can achieve much faster speed and lower storage than sparse representation, with limited performance loss compared with dense representation. Besides, our source codes have been publicly released for future research." @default.
- W3113287731 created "2020-12-21" @default.
- W3113287731 creator A5003799076 @default.
- W3113287731 creator A5014449192 @default.
- W3113287731 creator A5017626590 @default.
- W3113287731 creator A5018464968 @default.
- W3113287731 creator A5087631670 @default.
- W3113287731 date "2020-12-17" @default.
- W3113287731 modified "2023-09-29" @default.
- W3113287731 title "Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing" @default.
- W3113287731 cites W2053154970 @default.
- W3113287731 cites W2155482025 @default.
- W3113287731 cites W2218741211 @default.
- W3113287731 cites W2328886022 @default.
- W3113287731 cites W2411707397 @default.
- W3113287731 cites W2593864460 @default.
- W3113287731 cites W2798456655 @default.
- W3113287731 cites W2822830299 @default.
- W3113287731 cites W2891416139 @default.
- W3113287731 cites W2952813980 @default.
- W3113287731 cites W2963341956 @default.
- W3113287731 cites W2964178377 @default.
- W3113287731 cites W2967674528 @default.
- W3113287731 cites W2970648534 @default.
- W3113287731 cites W2985258882 @default.
- W3113287731 cites W2995289474 @default.
- W3113287731 cites W3021282678 @default.
- W3113287731 cites W3034744902 @default.
- W3113287731 cites W3038572442 @default.
- W3113287731 cites W3080973007 @default.
- W3113287731 cites W3100307207 @default.
- W3113287731 cites W836999996 @default.
- W3113287731 doi "https://doi.org/10.48550/arxiv.2012.09647" @default.
- W3113287731 hasPublicationYear "2020" @default.
- W3113287731 type Work @default.
- W3113287731 sameAs 3113287731 @default.
- W3113287731 citedByCount "1" @default.
- W3113287731 countsByYear W31132877312022 @default.
- W3113287731 crossrefType "posted-content" @default.
- W3113287731 hasAuthorship W3113287731A5003799076 @default.
- W3113287731 hasAuthorship W3113287731A5014449192 @default.
- W3113287731 hasAuthorship W3113287731A5017626590 @default.
- W3113287731 hasAuthorship W3113287731A5018464968 @default.
- W3113287731 hasAuthorship W3113287731A5087631670 @default.
- W3113287731 hasBestOaLocation W31132877311 @default.
- W3113287731 hasConcept C101738243 @default.
- W3113287731 hasConcept C108583219 @default.
- W3113287731 hasConcept C124101348 @default.
- W3113287731 hasConcept C154945302 @default.
- W3113287731 hasConcept C17744445 @default.
- W3113287731 hasConcept C199539241 @default.
- W3113287731 hasConcept C23123220 @default.
- W3113287731 hasConcept C2776359362 @default.
- W3113287731 hasConcept C38652104 @default.
- W3113287731 hasConcept C41008148 @default.
- W3113287731 hasConcept C67388219 @default.
- W3113287731 hasConcept C74270461 @default.
- W3113287731 hasConcept C81917197 @default.
- W3113287731 hasConcept C94625758 @default.
- W3113287731 hasConcept C99138194 @default.
- W3113287731 hasConceptScore W3113287731C101738243 @default.
- W3113287731 hasConceptScore W3113287731C108583219 @default.
- W3113287731 hasConceptScore W3113287731C124101348 @default.
- W3113287731 hasConceptScore W3113287731C154945302 @default.
- W3113287731 hasConceptScore W3113287731C17744445 @default.
- W3113287731 hasConceptScore W3113287731C199539241 @default.
- W3113287731 hasConceptScore W3113287731C23123220 @default.
- W3113287731 hasConceptScore W3113287731C2776359362 @default.
- W3113287731 hasConceptScore W3113287731C38652104 @default.
- W3113287731 hasConceptScore W3113287731C41008148 @default.
- W3113287731 hasConceptScore W3113287731C67388219 @default.
- W3113287731 hasConceptScore W3113287731C74270461 @default.
- W3113287731 hasConceptScore W3113287731C81917197 @default.
- W3113287731 hasConceptScore W3113287731C94625758 @default.
- W3113287731 hasConceptScore W3113287731C99138194 @default.
- W3113287731 hasLocation W31132877311 @default.
- W3113287731 hasOpenAccess W3113287731 @default.
- W3113287731 hasPrimaryLocation W31132877311 @default.
- W3113287731 hasRelatedWork W2065460148 @default.
- W3113287731 hasRelatedWork W2152607402 @default.
- W3113287731 hasRelatedWork W2156435549 @default.
- W3113287731 hasRelatedWork W2259768202 @default.
- W3113287731 hasRelatedWork W2369789896 @default.
- W3113287731 hasRelatedWork W2418353079 @default.
- W3113287731 hasRelatedWork W2734503711 @default.
- W3113287731 hasRelatedWork W3058139535 @default.
- W3113287731 hasRelatedWork W4317738359 @default.
- W3113287731 hasRelatedWork W2184871064 @default.
- W3113287731 isParatext "false" @default.
- W3113287731 isRetracted "false" @default.
- W3113287731 magId "3113287731" @default.
- W3113287731 workType "article" @default.