Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287774103> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4287774103 abstract "Measuring user satisfaction level is a challenging task, and a critical component in developing large-scale conversational agent systems serving the needs of real users. An widely used approach to tackle this is to collect human annotation data and use them for evaluation or modeling. Human annotation based approaches are easier to control, but hard to scale. A novel alternative approach is to collect user's direct feedback via a feedback elicitation system embedded to the conversational agent system, and use the collected user feedback to train a machine-learned model for generalization. User feedback is the best proxy for user satisfaction, but is not available for some ineligible intents and certain situations. Thus, these two types of approaches are complementary to each other. In this work, we tackle the user satisfaction assessment problem with a hybrid approach that fuses explicit user feedback, user satisfaction predictions inferred by two machine-learned models, one trained on user feedback data and the other human annotation data. The hybrid approach is based on a waterfall policy, and the experimental results with Amazon Alexa's large-scale datasets show significant improvements in inferring user satisfaction. A detailed hybrid architecture, an in-depth analysis on user feedback data, and an algorithm that generates data sets to properly simulate the live traffic are presented in this paper." @default.
- W4287774103 created "2022-07-26" @default.
- W4287774103 creator A5002270566 @default.
- W4287774103 creator A5010125493 @default.
- W4287774103 creator A5010305620 @default.
- W4287774103 creator A5030284025 @default.
- W4287774103 creator A5058394211 @default.
- W4287774103 creator A5059051692 @default.
- W4287774103 creator A5062736640 @default.
- W4287774103 creator A5065278133 @default.
- W4287774103 creator A5066368974 @default.
- W4287774103 creator A5072875068 @default.
- W4287774103 creator A5074290079 @default.
- W4287774103 creator A5079883225 @default.
- W4287774103 creator A5089742425 @default.
- W4287774103 date "2020-05-29" @default.
- W4287774103 modified "2023-10-12" @default.
- W4287774103 title "Large-scale Hybrid Approach for Predicting User Satisfaction with Conversational Agents" @default.
- W4287774103 doi "https://doi.org/10.48550/arxiv.2006.07113" @default.
- W4287774103 hasPublicationYear "2020" @default.
- W4287774103 type Work @default.
- W4287774103 citedByCount "1" @default.
- W4287774103 countsByYear W42877741032022 @default.
- W4287774103 crossrefType "posted-content" @default.
- W4287774103 hasAuthorship W4287774103A5002270566 @default.
- W4287774103 hasAuthorship W4287774103A5010125493 @default.
- W4287774103 hasAuthorship W4287774103A5010305620 @default.
- W4287774103 hasAuthorship W4287774103A5030284025 @default.
- W4287774103 hasAuthorship W4287774103A5058394211 @default.
- W4287774103 hasAuthorship W4287774103A5059051692 @default.
- W4287774103 hasAuthorship W4287774103A5062736640 @default.
- W4287774103 hasAuthorship W4287774103A5065278133 @default.
- W4287774103 hasAuthorship W4287774103A5066368974 @default.
- W4287774103 hasAuthorship W4287774103A5072875068 @default.
- W4287774103 hasAuthorship W4287774103A5074290079 @default.
- W4287774103 hasAuthorship W4287774103A5079883225 @default.
- W4287774103 hasAuthorship W4287774103A5089742425 @default.
- W4287774103 hasBestOaLocation W42877741031 @default.
- W4287774103 hasConcept C107457646 @default.
- W4287774103 hasConcept C111919701 @default.
- W4287774103 hasConcept C119857082 @default.
- W4287774103 hasConcept C121332964 @default.
- W4287774103 hasConcept C124101348 @default.
- W4287774103 hasConcept C134306372 @default.
- W4287774103 hasConcept C149229913 @default.
- W4287774103 hasConcept C154945302 @default.
- W4287774103 hasConcept C177148314 @default.
- W4287774103 hasConcept C201025465 @default.
- W4287774103 hasConcept C2776321320 @default.
- W4287774103 hasConcept C2778755073 @default.
- W4287774103 hasConcept C3017893058 @default.
- W4287774103 hasConcept C33923547 @default.
- W4287774103 hasConcept C41008148 @default.
- W4287774103 hasConcept C62520636 @default.
- W4287774103 hasConcept C63880386 @default.
- W4287774103 hasConcept C67712803 @default.
- W4287774103 hasConcept C89505385 @default.
- W4287774103 hasConceptScore W4287774103C107457646 @default.
- W4287774103 hasConceptScore W4287774103C111919701 @default.
- W4287774103 hasConceptScore W4287774103C119857082 @default.
- W4287774103 hasConceptScore W4287774103C121332964 @default.
- W4287774103 hasConceptScore W4287774103C124101348 @default.
- W4287774103 hasConceptScore W4287774103C134306372 @default.
- W4287774103 hasConceptScore W4287774103C149229913 @default.
- W4287774103 hasConceptScore W4287774103C154945302 @default.
- W4287774103 hasConceptScore W4287774103C177148314 @default.
- W4287774103 hasConceptScore W4287774103C201025465 @default.
- W4287774103 hasConceptScore W4287774103C2776321320 @default.
- W4287774103 hasConceptScore W4287774103C2778755073 @default.
- W4287774103 hasConceptScore W4287774103C3017893058 @default.
- W4287774103 hasConceptScore W4287774103C33923547 @default.
- W4287774103 hasConceptScore W4287774103C41008148 @default.
- W4287774103 hasConceptScore W4287774103C62520636 @default.
- W4287774103 hasConceptScore W4287774103C63880386 @default.
- W4287774103 hasConceptScore W4287774103C67712803 @default.
- W4287774103 hasConceptScore W4287774103C89505385 @default.
- W4287774103 hasLocation W42877741031 @default.
- W4287774103 hasOpenAccess W4287774103 @default.
- W4287774103 hasPrimaryLocation W42877741031 @default.
- W4287774103 hasRelatedWork W1590657835 @default.
- W4287774103 hasRelatedWork W181114622 @default.
- W4287774103 hasRelatedWork W2120494243 @default.
- W4287774103 hasRelatedWork W2288950015 @default.
- W4287774103 hasRelatedWork W2741711008 @default.
- W4287774103 hasRelatedWork W2751424329 @default.
- W4287774103 hasRelatedWork W2786397983 @default.
- W4287774103 hasRelatedWork W2808833968 @default.
- W4287774103 hasRelatedWork W3048212026 @default.
- W4287774103 hasRelatedWork W371613942 @default.
- W4287774103 isParatext "false" @default.
- W4287774103 isRetracted "false" @default.
- W4287774103 workType "article" @default.