SOGO: A Social Intelligent Negotiation Dialogue System

In this paper, we propose a semi-automatic social intelligent negotiation dialogue system that interweaves task utterance with conversational strategies to engage human users in negotiation. Our two-phase system operates sequentially in a reasoning-and-generation loop: In the task phase, we leverage an off-the-shelf end-to-end dialogue model for negotiation to build a dialogue manager which decides the next system's task intention. Then, during the social phase, we employ a theory-driven, template-based natural language generator to realize the task intention as a genre of social conversational strategy. Subsequently, a set of conversational strategies are presented to a human expert who decides the final sentence to be uttered by the dialogue system. Compared to the baseline system, our proposed social intelligent dialogue system achieves a higher agreement rate and more "good deals" with humans while building interpersonal rapport.

[1]  Alexander Peysakhovich,et al.  Maintaining cooperation in complex social dilemmas using deep reinforcement learning , 2017, ArXiv.

[2]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[3]  Ran Zhao,et al.  Towards a Dyadic Computational Model of Rapport Management for Human-Virtual Agent Interaction , 2014, IVA.

[4]  Stacy Marsella,et al.  Virtual Rapport , 2006, IVA.

[5]  Alexander I. Rudnicky,et al.  Learning Conversational Systems that Interleave Task and Non-Task Content , 2017, IJCAI.

[6]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[7]  Pattie Maes,et al.  Agent-Mediated Integrative Negotiation for Retail Electronic Commerce , 1998, AMET.

[8]  Ran Zhao,et al.  Socially-Aware Virtual Agents: Automatically Assessing Dyadic Rapport from Temporal Patterns of Behavior , 2016, IVA.

[9]  Joseph B. Walther,et al.  The Impacts of Emoticons on Message Interpretation in Computer-Mediated Communication , 2001 .

[10]  Landra L. Rezabek,et al.  Visual Cues in Computer-Mediated Communication: Supplementing Text with Emoticons , 1998 .

[11]  Timothy W. Bickmore,et al.  Empirical Validation of an Accommodation Theory-Based Model of User-Agent Relationship , 2012, IVA.

[12]  Elite Olshtain,et al.  Requests and Apologies: A Cross-Cultural Study of Speech Act Realization Patterns (CCSARP)1 , 1984 .

[13]  Shou-De Lin,et al.  Designing Non-greedy Reinforcement Learning Agents with Diminishing Reward Shaping , 2018, AIES.

[14]  Amy Ogan,et al.  Rudeness and Rapport: Insults and Learning Gains in Peer Tutoring , 2012, ITS.

[15]  Ido Dagan,et al.  The Negochat Corpus of Human-agent Negotiation Dialogues , 2016, LREC.

[16]  David DeVault,et al.  Towards An Autonomous Agent that Provides Automated Feedback on Students' Negotiation Skills , 2017, AAMAS.

[17]  Candace L. Sidner,et al.  Activity Planning for Long-Term Relationships , 2013 .

[18]  Zohar Livnat,et al.  Rapport in Negotiation , 2012 .

[19]  Janice Nadler.  Rapport in Negotiation and Conflict Resolution , 2004 .

[20]  Ran Zhao,et al.  Cognitive-Inspired Conversational-Strategy Reasoner for Socially-Aware Agents , 2017, IJCAI.

[21]  Jonathan Gratch,et al.  Trust me: multimodal signals of trustworthiness , 2016, ICMI.

[22]  David DeVault,et al.  Toward Natural Turn-Taking in a Virtual Human Negotiation Agent , 2015, AAAI Spring Symposia.

[23]  Nicholas R. Jennings,et al.  Negotiation decision functions for autonomous agents , 1998, Robotics Auton. Syst..

[24]  Helen Spencer-Oatey,et al.  Face, (Im)Politeness and Rapport , 2008, Culturally Speaking Second Edition.

[25]  Louis-Philippe Morency,et al.  Virtual Rapport 2.0 , 2011, IVA.

[26]  David DeVault,et al.  Negotiation as a Challenge Problem for Virtual Humans , 2015, IVA.

[27]  Carles Sierra,et al.  DipGame: A challenging negotiation testbed , 2011, Eng. Appl. Artif. Intell..

[28]  S. Herring,et al.  Functions of the Nonverbal in CMC: Emoticons and Illocutionary Force , 2010 .

[29]  M. Eisenstein,et al.  ‘I Very Appreciate’: Expressions of Gratitude by Native and Non-native Speakers of American English , 1986 .

[30]  L. M. Beebe,et al.  Sociolinguistic Variation in Face-Threatening Speech Acts , 1989 .

[31]  Jonathan Gratch,et al.  IAGO: Interactive Arbitration Guide Online , 2016, AAMAS 2016.

[32]  Ran Zhao,et al.  Socially-Aware Animated Intelligent Personal Assistant Agent , 2016, SIGDIAL Conference.

[33]  Ipke Wachsmuth,et al.  Small Talk Is More than Chit-Chat - Exploiting Structures of Casual Conversations for a Virtual Agent , 2012, KI.

[34]  P. Ekman,et al.  A new pan-cultural facial expression of emotion , 1986 .

[35]  Sarit Kraus,et al.  Genius: negotiation environment for heterogeneous agents , 2009, AAMAS.

[36]  H. Spencer-Oatey.  Culturally speaking : culture, communication and politeness theory , 2008 .

[37]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[38]  Yann Dauphin,et al.  Deal or No Deal? End-to-End Learning of Negotiation Dialogues , 2017, EMNLP.

[39]  Justine Cassell,et al.  Relational agents: a model and implementation of building user trust , 2001, CHI.

[40]  L. Tickle-Degnen,et al.  The Nature of Rapport and Its Nonverbal Correlates , 1990 .

[41]  D. Ferrin,et al.  Interpersonal trust within negotiations: : Meta-analytic evidence, critical contingencies, and directions for future research. , 2014 .

[42]  Jonathan Gratch,et al.  Pinocchio : Answering Human-Agent Negotiation Questions through Realistic Agent Design , 2017 .

[43]  Hillary Anger Elfenbein,et al.  What Do People Value When They Negotiate? Mapping the Domain of Subjective Value in Negotiation , 2006, Journal of personality and social psychology.