TY - GEN
T1 - Transformer-based Empathetic Response Generation Using Dialogue Situation and Advanced-Level Definition of Empathy
AU - Wang, Yi Hsuan
AU - Hsu, Jia Hao
AU - Wu, Chung Hsien
AU - Yang, Tsung Hsien
N1 - Funding Information:
The authors would like to express our gratitude to Dr. Shinichi Ohtsuki (Professor of Division of Pediatric Cardiology, Department of Pediatrics, Okayama University Hospital) and Dr. Hidemasa Oh (Professor of Department of Regenerative Medicine, Center for Innovative Clinical Medicine, Okayama University Hospital) for making an opportunity to carry out MRI examinations.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/1/24
Y1 - 2021/1/24
N2 - This study proposes an approach to transformer-based empathetic response generation using dialogue situation and advanced-level definition of empathy. First, SBERT is adopted to extract the dialog situation vector from the user's historical sentences. A BERT-based emotion detector, a topic detector and an information estimator are constructed for empathy-related feature extraction. The change of the emotional valance and the textual information gain, obtained from the emotion detector and the information estimator, are used for adversarial training of the transformer-based empathetic response generator. The loss function of the transformer is defined to measure how good the expected response in terms of fluency and empathy. The EmpatheticDialogues corpus was adopted for system training and evaluation on empathetic response generation. According to the experimental results, the BLEU score was increased to 7.821 after considering the dialogue situation feature and empathy definition, outperforming the comparison models. In terms of human subjective evaluation, three evaluation results of empathy, relevance and fluency for the proposed system are better than that for the baseline model.
AB - This study proposes an approach to transformer-based empathetic response generation using dialogue situation and advanced-level definition of empathy. First, SBERT is adopted to extract the dialog situation vector from the user's historical sentences. A BERT-based emotion detector, a topic detector and an information estimator are constructed for empathy-related feature extraction. The change of the emotional valance and the textual information gain, obtained from the emotion detector and the information estimator, are used for adversarial training of the transformer-based empathetic response generator. The loss function of the transformer is defined to measure how good the expected response in terms of fluency and empathy. The EmpatheticDialogues corpus was adopted for system training and evaluation on empathetic response generation. According to the experimental results, the BLEU score was increased to 7.821 after considering the dialogue situation feature and empathy definition, outperforming the comparison models. In terms of human subjective evaluation, three evaluation results of empathy, relevance and fluency for the proposed system are better than that for the baseline model.
UR - http://www.scopus.com/inward/record.url?scp=85102588591&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102588591&partnerID=8YFLogxK
U2 - 10.1109/ISCSLP49672.2021.9362067
DO - 10.1109/ISCSLP49672.2021.9362067
M3 - Conference contribution
AN - SCOPUS:85102588591
T3 - 2021 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021
BT - 2021 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th International Symposium on Chinese Spoken Language Processing, ISCSLP 2021
Y2 - 24 January 2021 through 27 January 2021
ER -