Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose Emotional Chatting Machine (ECM) that can generate appropriate responses not only in content (relevant and grammatical) but also in emotion (emotionally consistent). To the best of our knowledge, this is the first work that addresses the emotion factor in large-scale conversation generation. ECM addresses the factor using three new mechanisms that respectively (1) models the high-level abstraction of emotion expressions by embedding emotion categories, (2) captures the change of implicit internal emotion states, and (3) uses explicit emotion expressions with an external emotion vocabulary. Experiments show that the proposed model can generate responses appropriate not only in content but also in emotion.

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

[2]  Jianfeng Gao,et al.  A Persona-Based Neural Conversation Model , 2016, ACL.

[3]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[4]  David Konopnicki,et al.  Neural Response Generation for Customer Service based on Personality Traits , 2017, INLG.

[5]  Hang Li,et al.  A Deep Memory-based Architecture for Sequence-to-Sequence Learning , 2015 .

[6]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[7]  Fei Liu,et al.  Dialog state tracking, a machine reading approach using Memory Network , 2016, EACL.

[8]  Firoj Alam,et al.  Annotating and modeling empathy in spoken conversations , 2017, Comput. Speech Lang..

[9]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[10]  Alan Ritter,et al.  Data-Driven Response Generation in Social Media , 2011, EMNLP.

[11]  Denny Britz,et al.  Generating Long and Diverse Responses with Neural Conversation Models , 2017, ArXiv.

[12]  Joelle Pineau,et al.  Hierarchical Neural Network Generative Models for Movie Dialogues , 2015, ArXiv.

[13]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[14]  J. Fleiss Measuring nominal scale agreement among many raters. , 1971 .

[15]  Mathias Theunis,et al.  The Good, the Bad and the Neutral: Affective Profile in Dialog System-User Communication , 2011, ACII.

[16]  Hang Li,et al.  Neural Responding Machine for Short-Text Conversation , 2015, ACL.

[18]  Jan Treur On Human Aspects in Ambient Intelligence , 2007, AmI Workshops.

[19]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[20]  Mitsuru Ishizuka,et al.  THE EMPATHIC COMPANION: A CHARACTER-BASED INTERFACE THAT ADDRESSES USERS' AFFECTIVE STATES , 2005, Appl. Artif. Intell..

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

[22]  Louis-Philippe Morency,et al.  Affect-LM: A Neural Language Model for Customizable Affective Text Generation , 2017, ACL.

[23]  Pawel Dybala,et al.  Towards Context Aware Emotional Intelligence in Machines: Computing Contextual Appropriateness of Affective States , 2009, IJCAI.

[24]  Jürgen Schmidhuber,et al.  Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition , 2005, ICANN.

[25]  Veikko Surakka,et al.  The effects of affective interventions in human-computer interaction , 2004, Interact. Comput..

[26]  R. Gunderman,et al.  Emotional intelligence. , 2011, Journal of the American College of Radiology : JACR.

[27]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[28]  Xiang Li,et al.  Two are Better than One: An Ensemble of Retrieval- and Generation-Based Dialog Systems , 2016, ArXiv.

[29]  Ming Li,et al.  Neural Contextual Conversation Learning with Labeled Question-Answering Pairs , 2016, ArXiv.

[30]  Sigal G. Barsade,et al.  Human abilities: emotional intelligence. , 2008, Annual review of psychology.

[31]  Rui Yan,et al.  Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation , 2016, COLING.

[32]  Reut Tsarfaty,et al.  Data-Driven Broad-Coverage Grammars for Opinionated Natural Language Generation (ONLG) , 2017, ACL.

[33]  Eric P. Xing,et al.  Toward Controlled Generation of Text , 2017, ICML.

[34]  Mitsuru Ishizuka,et al.  Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game , 2005, Int. J. Hum. Comput. Stud..

[35]  Jason Weston,et al.  Key-Value Memory Networks for Directly Reading Documents , 2016, EMNLP.

[36]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

[37]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[38]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[39]  Alex Waibel,et al.  EMOTION-SENSITIVE HUMAN-COMPUTER INTERFACES , 2000 .

[40]  Alex Graves,et al.  Neural Turing Machines , 2014, ArXiv.

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

[42]  J. Koenderink Q… , 2014, Les noms officiels des communes de Wallonie, de Bruxelles-Capitale et de la communaute germanophone.

[43]  J. Gross The Emerging Field of Emotion Regulation: An Integrative Review , 1998 .

[44]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

[45]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[46]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[47]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[48]  Joelle Pineau,et al.  How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation , 2016, EMNLP.

[49]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[50]  Lukás Burget,et al.  Recurrent neural network based language model , 2010, INTERSPEECH.

[51]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[52]  Marcin Skowron,et al.  Affect Listeners: Acquisition of Affective States by Means of Conversational Systems , 2009, COST 2102 Training School.

[53]  A. Hochschild Emotion Work, Feeling Rules, and Social Structure , 1979, American Journal of Sociology.

[54]  Daniel Jurafsky,et al.  A Simple, Fast Diverse Decoding Algorithm for Neural Generation , 2016, ArXiv.

[55]  Wolfgang Minker,et al.  Endowing Spoken Language Dialogue Systems with Emotional Intelligence , 2004, ADS.