TY - JOUR
T1 - Interaction Style Recognition Based on Multi-Layer Multi-View Profile Representation
AU - Wei, Wen Li
AU - Lin, Jen Chun
AU - Wu, Chung Hsien
N1 - Funding Information:
This work was supported in part by the Ministry of Science and Technology under Contract MOST102-2221-E-006-094-MY3 and the Headquarters of University Advancement at the National Cheng Kung University, which is sponsored by the Ministry of Education, Taiwan.
Publisher Copyright:
© 2010-2012 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Interaction Style (IS) refers to patterns of interaction containing highly contextual and innate information. Awareness of our IS can help us discover interpersonal conflicts and guide us how to interact with others. Recently, automatic IS recognition is becoming increasingly important in the design of a dialogue system for harmonious interaction. With the goal to select appropriate responses, four IS types proposed by Berens are selected as the basis for our study. In this study, multiple views (multi-views) of the utterances during interaction, including emotions and dialogue topics, are recognized first. Inspired by the emotion profile theory, the IS profiles are then extracted using the multi-view features to better characterize the IS of the interactional utterances. Similar to the multilayer architectures in deep neural networks, a multi-layer multi-view IS profile representation method, structured layer by layer through embedding the multi-views, is proposed to better interpret intermediate representations in the feature space of the interactional utterances based on a probabilistic fusion model. The IS is finally recognized by using the Support Vector Machine (SVM) based on the obtained IS profiles. Experimental results demonstrate that the proposed method achieved an encouraging IS recognition accuracy and outperformed the previous method.
AB - Interaction Style (IS) refers to patterns of interaction containing highly contextual and innate information. Awareness of our IS can help us discover interpersonal conflicts and guide us how to interact with others. Recently, automatic IS recognition is becoming increasingly important in the design of a dialogue system for harmonious interaction. With the goal to select appropriate responses, four IS types proposed by Berens are selected as the basis for our study. In this study, multiple views (multi-views) of the utterances during interaction, including emotions and dialogue topics, are recognized first. Inspired by the emotion profile theory, the IS profiles are then extracted using the multi-view features to better characterize the IS of the interactional utterances. Similar to the multilayer architectures in deep neural networks, a multi-layer multi-view IS profile representation method, structured layer by layer through embedding the multi-views, is proposed to better interpret intermediate representations in the feature space of the interactional utterances based on a probabilistic fusion model. The IS is finally recognized by using the Support Vector Machine (SVM) based on the obtained IS profiles. Experimental results demonstrate that the proposed method achieved an encouraging IS recognition accuracy and outperformed the previous method.
UR - http://www.scopus.com/inward/record.url?scp=85029940379&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029940379&partnerID=8YFLogxK
U2 - 10.1109/TAFFC.2016.2553024
DO - 10.1109/TAFFC.2016.2553024
M3 - Article
AN - SCOPUS:85029940379
VL - 8
SP - 355
EP - 368
JO - IEEE Transactions on Affective Computing
JF - IEEE Transactions on Affective Computing
SN - 1949-3045
IS - 3
M1 - 7450642
ER -