Matches in SemOpenAlex for { <https://semopenalex.org/work/W2980479057> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2980479057 abstract "This paper presents multimodal computational modeling of three labels that are independently annotated per exchange to implement an adaptation mechanism of dialogue strategy in spoken dialogue systems based on recognizing user sentiment by multimodal signal processing. The three labels include (1) user’s interest label pertaining to the current topic, (2) user’s sentiment label, and (3) topic continuance denoting whether the system should continue the current topic or change it. Predicting the three types of labels that capture different aspects of the user’s sentiment level and the system’s next action contribute to adopting a dialogue strategy based on the user’s sentiment. For this purpose, we enhanced shared multimodal dialogue data by annotating impressed sentiment labels and the topic continuance labels. With the corpus, we develop a multimodal prediction model for the three labels. A multitask learning technique is applied for binary classification tasks of the three labels considering the partial similarities among them. The prediction model was efficiently trained even with a small data set (less than 2000 samples) thanks to the multitask learning framework. Experimental results show that the multitask deep neural network (DNN) model trained with multimodal features including linguistics, facial expressions, body and head motions, and acoustic features, outperformed those trained as single-task DNNs by 1.6 points at the maximum." @default.
- W2980479057 created "2019-10-25" @default.
- W2980479057 creator A5040835131 @default.
- W2980479057 creator A5049614400 @default.
- W2980479057 creator A5080920610 @default.
- W2980479057 creator A5091448873 @default.
- W2980479057 date "2019-10-14" @default.
- W2980479057 modified "2023-10-16" @default.
- W2980479057 title "Multitask Prediction of Exchange-level Annotations for Multimodal Dialogue Systems" @default.
- W2980479057 cites W1981688737 @default.
- W2980479057 cites W2067360832 @default.
- W2980479057 cites W2074788634 @default.
- W2980479057 cites W2102759648 @default.
- W2980479057 cites W2145421863 @default.
- W2980479057 cites W2164777277 @default.
- W2980479057 cites W2187036766 @default.
- W2980479057 cites W2215376118 @default.
- W2980479057 cites W2251397886 @default.
- W2980479057 cites W2526567570 @default.
- W2980479057 cites W2555691756 @default.
- W2980479057 cites W2743233975 @default.
- W2980479057 cites W2755232679 @default.
- W2980479057 cites W2890248990 @default.
- W2980479057 cites W2894609524 @default.
- W2980479057 cites W2895232831 @default.
- W2980479057 cites W2895434601 @default.
- W2980479057 cites W2913340405 @default.
- W2980479057 cites W3209042722 @default.
- W2980479057 cites W4239510810 @default.
- W2980479057 doi "https://doi.org/10.1145/3340555.3353730" @default.
- W2980479057 hasPublicationYear "2019" @default.
- W2980479057 type Work @default.
- W2980479057 sameAs 2980479057 @default.
- W2980479057 citedByCount "8" @default.
- W2980479057 countsByYear W29804790572020 @default.
- W2980479057 countsByYear W29804790572021 @default.
- W2980479057 countsByYear W29804790572022 @default.
- W2980479057 countsByYear W29804790572023 @default.
- W2980479057 crossrefType "proceedings-article" @default.
- W2980479057 hasAuthorship W2980479057A5040835131 @default.
- W2980479057 hasAuthorship W2980479057A5049614400 @default.
- W2980479057 hasAuthorship W2980479057A5080920610 @default.
- W2980479057 hasAuthorship W2980479057A5091448873 @default.
- W2980479057 hasConcept C119857082 @default.
- W2980479057 hasConcept C120665830 @default.
- W2980479057 hasConcept C121332964 @default.
- W2980479057 hasConcept C12267149 @default.
- W2980479057 hasConcept C139807058 @default.
- W2980479057 hasConcept C154945302 @default.
- W2980479057 hasConcept C162324750 @default.
- W2980479057 hasConcept C177264268 @default.
- W2980479057 hasConcept C187736073 @default.
- W2980479057 hasConcept C199360897 @default.
- W2980479057 hasConcept C204321447 @default.
- W2980479057 hasConcept C2780451532 @default.
- W2980479057 hasConcept C41008148 @default.
- W2980479057 hasConcept C66402592 @default.
- W2980479057 hasConcept C66905080 @default.
- W2980479057 hasConceptScore W2980479057C119857082 @default.
- W2980479057 hasConceptScore W2980479057C120665830 @default.
- W2980479057 hasConceptScore W2980479057C121332964 @default.
- W2980479057 hasConceptScore W2980479057C12267149 @default.
- W2980479057 hasConceptScore W2980479057C139807058 @default.
- W2980479057 hasConceptScore W2980479057C154945302 @default.
- W2980479057 hasConceptScore W2980479057C162324750 @default.
- W2980479057 hasConceptScore W2980479057C177264268 @default.
- W2980479057 hasConceptScore W2980479057C187736073 @default.
- W2980479057 hasConceptScore W2980479057C199360897 @default.
- W2980479057 hasConceptScore W2980479057C204321447 @default.
- W2980479057 hasConceptScore W2980479057C2780451532 @default.
- W2980479057 hasConceptScore W2980479057C41008148 @default.
- W2980479057 hasConceptScore W2980479057C66402592 @default.
- W2980479057 hasConceptScore W2980479057C66905080 @default.
- W2980479057 hasLocation W29804790571 @default.
- W2980479057 hasOpenAccess W2980479057 @default.
- W2980479057 hasPrimaryLocation W29804790571 @default.
- W2980479057 hasRelatedWork W2081647779 @default.
- W2980479057 hasRelatedWork W3107474891 @default.
- W2980479057 hasRelatedWork W3185852197 @default.
- W2980479057 hasRelatedWork W3192794374 @default.
- W2980479057 hasRelatedWork W3215867059 @default.
- W2980479057 hasRelatedWork W4235763504 @default.
- W2980479057 hasRelatedWork W4281608370 @default.
- W2980479057 hasRelatedWork W4285815787 @default.
- W2980479057 hasRelatedWork W4360986142 @default.
- W2980479057 hasRelatedWork W4362613237 @default.
- W2980479057 isParatext "false" @default.
- W2980479057 isRetracted "false" @default.
- W2980479057 magId "2980479057" @default.
- W2980479057 workType "article" @default.