FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765963752> ?p ?o ?g. }

• W2765963752 abstract "We study the problem of response selection for multi-turn conversation in retrieval-based chatbots. The task requires matching a response candidate with a conversation context, whose challenges include how to recognize important parts of the context, and how to model the relationships among utterances in the context. Existing matching methods may lose important information in contexts as we can interpret them with a unified framework in which contexts are transformed to fixed-length vectors without any interaction with responses before matching. The analysis motivates us to propose a new matching framework that can sufficiently carry the important information in contexts to matching and model the relationships among utterances at the same time. The new framework, which we call a sequential matching framework (SMF), lets each utterance in a context interacts with a response candidate at the first step and transforms the pair to a matching vector. The matching vectors are then accumulated following the order of the utterances in the context with a recurrent neural network (RNN) which models the relationships among the utterances. The context-response matching is finally calculated with the hidden states of the RNN. Under SMF, we propose a sequential convolutional network and sequential attention network and conduct experiments on two public data sets to test their performance. Experimental results show that both models can significantly outperform the state-of-the-art matching methods. We also show that the models are interpretable with visualizations that provide us insights on how they capture and leverage the important information in contexts for matching." @default.
• W2765963752 created "2017-11-10" @default.
• W2765963752 creator A5013997063 @default.
• W2765963752 creator A5033532580 @default.
• W2765963752 creator A5036786337 @default.
• W2765963752 creator A5045556326 @default.
• W2765963752 creator A5049732922 @default.
• W2765963752 creator A5058189738 @default.
• W2765963752 date "2017-10-31" @default.
• W2765963752 modified "2023-09-27" @default.
• W2765963752 title "A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots" @default.
• W2765963752 cites W10957333 @default.
• W2765963752 cites W1522301498 @default.
• W2765963752 cites W1591706642 @default.
• W2765963752 cites W1910529161 @default.
• W2765963752 cites W1924770834 @default.
• W2765963752 cites W1966443646 @default.
• W2765963752 cites W1975879668 @default.
• W2765963752 cites W2008353316 @default.
• W2765963752 cites W2064675550 @default.
• W2765963752 cites W2086511124 @default.
• W2765963752 cites W2102531443 @default.
• W2765963752 cites W2110485445 @default.
• W2765963752 cites W2115101920 @default.
• W2765963752 cites W2118463056 @default.
• W2765963752 cites W2127426251 @default.
• W2765963752 cites W2131876387 @default.
• W2765963752 cites W2136189984 @default.
• W2765963752 cites W2159640018 @default.
• W2765963752 cites W2161466446 @default.
• W2765963752 cites W2170738476 @default.
• W2765963752 cites W2173361515 @default.
• W2765963752 cites W2197546379 @default.
• W2765963752 cites W2221711388 @default.
• W2765963752 cites W2250539671 @default.
• W2765963752 cites W2250889812 @default.
• W2765963752 cites W2251241778 @default.
• W2765963752 cites W2265289447 @default.
• W2765963752 cites W2291880741 @default.
• W2765963752 cites W2311783643 @default.
• W2765963752 cites W2338325072 @default.
• W2765963752 cites W2339852062 @default.
• W2765963752 cites W2384495648 @default.
• W2765963752 cites W2399880602 @default.
• W2765963752 cites W2402336193 @default.
• W2765963752 cites W2410983263 @default.
• W2765963752 cites W2413794162 @default.
• W2765963752 cites W2418993857 @default.
• W2765963752 cites W2469060249 @default.
• W2765963752 cites W2470875822 @default.
• W2765963752 cites W2511929605 @default.
• W2765963752 cites W2512531235 @default.
• W2765963752 cites W2605133118 @default.
• W2765963752 cites W2608787653 @default.
• W2765963752 cites W2891416139 @default.
• W2765963752 cites W2949541494 @default.
• W2765963752 cites W2950133940 @default.
• W2765963752 cites W2951520714 @default.
• W2765963752 cites W2951528484 @default.
• W2765963752 cites W2951580200 @default.
• W2765963752 cites W2953150860 @default.
• W2765963752 cites W295828404 @default.
• W2765963752 cites W2962883855 @default.
• W2765963752 cites W2964308564 @default.
• W2765963752 cites W836999996 @default.
• W2765963752 doi "https://doi.org/10.48550/arxiv.1710.11344" @default.
• W2765963752 hasPublicationYear "2017" @default.
• W2765963752 type Work @default.
• W2765963752 sameAs 2765963752 @default.
• W2765963752 citedByCount "1" @default.
• W2765963752 countsByYear W27659637522018 @default.
• W2765963752 crossrefType "posted-content" @default.
• W2765963752 hasAuthorship W2765963752A5013997063 @default.
• W2765963752 hasAuthorship W2765963752A5033532580 @default.
• W2765963752 hasAuthorship W2765963752A5036786337 @default.
• W2765963752 hasAuthorship W2765963752A5045556326 @default.
• W2765963752 hasAuthorship W2765963752A5049732922 @default.
• W2765963752 hasAuthorship W2765963752A5058189738 @default.
• W2765963752 hasBestOaLocation W27659637521 @default.
• W2765963752 hasConcept C105795698 @default.
• W2765963752 hasConcept C119857082 @default.
• W2765963752 hasConcept C144024400 @default.
• W2765963752 hasConcept C151730666 @default.
• W2765963752 hasConcept C153083717 @default.
• W2765963752 hasConcept C154945302 @default.
• W2765963752 hasConcept C162324750 @default.
• W2765963752 hasConcept C165064840 @default.
• W2765963752 hasConcept C187736073 @default.
• W2765963752 hasConcept C2775852435 @default.
• W2765963752 hasConcept C2777200299 @default.
• W2765963752 hasConcept C2779343474 @default.
• W2765963752 hasConcept C2780451532 @default.
• W2765963752 hasConcept C33923547 @default.
• W2765963752 hasConcept C41008148 @default.
• W2765963752 hasConcept C44291984 @default.
• W2765963752 hasConcept C46312422 @default.
• W2765963752 hasConcept C86803240 @default.
• W2765963752 hasConceptScore W2765963752C105795698 @default.
• W2765963752 hasConceptScore W2765963752C119857082 @default.
• W2765963752 hasConceptScore W2765963752C144024400 @default.

• next