Optimizing Neural Response Generator with Emotional Impact Information

The potential of dialogue systems to address user’s emotional need has steadily grown. In particular, we focus on dialogue systems application to promote positive emotional states, similar to that of emotional support between humans. Positive emotion elicitation takes form as chat-based dialogue interactions that is layered with an implicit goal to improve user’s emotional state. To this date, existing approaches have only relied on mimicking the target responses without considering their emotional impact, i.e. the change of emotional state they cause on the listener, in the model itself. In this paper, we propose explicitly utilizing emotional impact information to optimize neural dialogue system towards generating responses that elicit positive emotion. We examine two emotion-rich corpora with different data collection scenarios: Wizard-of-Oz and spontaneous. Evaluation shows that the proposed method yields lower perplexity, as well as produces responses that are perceived as more natural and likely to elicit a more positive emotion.

[1]  J. Russell.  A circumplex model of affect. , 1980 .

[2]  Joelle Pineau,et al.  Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models , 2015, AAAI.

[3]  Pierre Philippot,et al.  Selective effects of emotion on the phenomenal characteristics of autobiographical memories , 2005, Memory.

[4]  Tomoki Toda,et al.  Utilizing Human-to-Human Conversation Examples for a Multi Domain Chat-Oriented Dialog System , 2014, IEICE Trans. Inf. Syst..

[5]  Jaime C. Acosta,et al.  Achieving rapport with turn-by-turn, user-responsive emotional coloring , 2011, Speech Commun..

[6]  Joelle Pineau,et al.  A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues , 2016, AAAI.

[7]  Helen F. Hastie,et al.  A survey on metrics for the evaluation of user simulations , 2012, The Knowledge Engineering Review.

[8]  Jonathan Klein,et al.  Computers that recognise and respond to user emotion: theoretical and practical implications , 2002, Interact. Comput..

[9]  Quoc V. Le,et al.  A Neural Conversational Model , 2015, ArXiv.

[10]  Satoshi Nakamura,et al.  Eliciting Positive Emotional Impact in Dialogue Response Selection , 2018, IWSDS.

[11]  Diane J. Litman,et al.  Adapting to Multiple Affective States in Spoken Dialogue , 2012, SIGDIAL Conference.

[12]  Satoshi Nakamura,et al.  Eliciting Positive Emotion through Affect-Sensitive Dialogue Response Generation: A Neural Network Approach , 2018, AAAI.

[13]  A. Manstead,et al.  Social sharing of emotion following exposure to a negatively valenced situation , 2000 .

[14]  J. Gross,et al.  Emotion elicitation using films , 1995 .

[15]  Arvid Kappas,et al.  Affect and Social Processes in Online Communication--Experiments with an Affective Dialog System , 2013, IEEE Transactions on Affective Computing.

[16]  B. Mesquita,et al.  Beyond the emotional event: Six studies on the social sharing of emotion , 1991 .

[17]  John-Jules Ch. Meyer,et al.  Adaptive Emotional Expression in Robot-Child Interaction , 2014, 2014 9th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[18]  Nadia Magnenat-Thalmann,et al.  Generic personality and emotion simulation for conversational agents , 2004, Comput. Animat. Virtual Worlds.

[19]  Xiaoyan Zhu,et al.  Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory , 2017, AAAI.

[20]  Maja Pantic,et al.  This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. IEEE TRANSACTIONS ON AFFECTIVE COMPUTING , 2022 .

[21]  Nobuhiro Kaji,et al.  Predicting and Eliciting Addressee's Emotion in Online Dialogue , 2013, ACL.

[22]  Jianfeng Gao,et al.  A Neural Network Approach to Context-Sensitive Generation of Conversational Responses , 2015, NAACL.

[23]  David DeVault,et al.  The Distress Analysis Interview Corpus of human and computer interviews , 2014, LREC.

[24]  Satoshi Nakamura,et al.  Dialogue Scenario Collection of Persuasive Dialogue with Emotional Expressions via Crowdsourcing , 2018, LREC.

[25]  Sangdo Han,et al.  Micro-Counseling Dialog System Based on Semantic Content , 2015, Natural Language Dialog Systems and Intelligent Assistants.

[26]  Björn W. Schuller,et al.  Building Autonomous Sensitive Artificial Listeners , 2012, IEEE Transactions on Affective Computing.

[27]  Roddy Cowie,et al.  FEELTRACE: an instrument for recording perceived emotion in real time , 2000 .

[28]  Ryuichiro Higashinaka,et al.  Effects of self-disclosure and empathy in human-computer dialogue , 2008, 2008 IEEE Spoken Language Technology Workshop.

[29]  A. Schaefer,et al.  Please Scroll down for Article Cognition & Emotion Assessing the Effectiveness of a Large Database of Emotion-eliciting Films: a New Tool for Emotion Researchers , 2022 .