Migratable AI: Personalizing Dialog Conversations with migration context

The migration of conversational AI agents across different embodiments in order to maintain the continuity of the task has been recently explored to further improve user experience. However, these migratable agents lack contextual understanding of the user information and the migrated device during the dialog conversations with the user. This opens the question of how an agent might behave when migrated into an embodiment for contextually predicting the next utterance. We collected a dataset from the dialog conversations between crowdsourced workers with the migration context involving personal and non-personal utterances in different settings (public or private) of embodiment into which the agent migrated. We trained the generative and information retrieval models on the dataset using with and without migration context and report the results of both qualitative metrics and human evaluation. We believe that the migration dataset would be useful for training future migratable AI systems.

[1]  John F. Bradley,et al.  Agent chameleons: agent minds and bodies , 2003, Proceedings 11th IEEE International Workshop on Program Comprehension.

[2]  Milica Gasic,et al.  The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management , 2010, Comput. Speech Lang..

[3]  Antoine Raux,et al.  The Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

[4]  Stefan Ultes,et al.  MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling , 2018, EMNLP.

[5]  Joelle Pineau,et al.  Generative Deep Neural Networks for Dialogue: A Short Review , 2016, ArXiv.

[6]  Don Lincoln,et al.  The Big Bang Theory , 2014 .

[7]  Haoyu Song,et al.  Exploiting Persona Information for Diverse Generation of Conversational Responses , 2019, IJCAI.

[8]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

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

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

[11]  John Zimmerman,et al.  Speed Dating: Providing a Menu of Possible Futures , 2017 .

[12]  Stephen Clark,et al.  A New Corpus and Imitation Learning Framework for Context-Dependent Semantic Parsing , 2014, TACL.

[13]  Mihail Eric,et al.  MultiWOZ 2. , 2019 .

[14]  Dilek Z. Hakkani-Tür,et al.  MultiWOZ 2.1: Multi-Domain Dialogue State Corrections and State Tracking Baselines , 2019, ArXiv.

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

[16]  David Vandyke,et al.  Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems , 2015, EMNLP.

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

[18]  Bill Byrne,et al.  Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset , 2019, EMNLP.

[19]  T. Ono,et al.  Agent migration: communications between a human and robot , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[20]  John Zimmerman,et al.  Re-Embodiment and Co-Embodiment: Exploration of social presence for robots and conversational agents , 2019, Conference on Designing Interactive Systems.

[21]  David Vandyke,et al.  Multi-domain Dialog State Tracking using Recurrent Neural Networks , 2015, ACL.

[22]  Cynthia Breazeal,et al.  Migratable AI: Effect of identity and information migration on users' perception of conversational AI agents , 2020, 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).

[23]  Boi Faltings,et al.  Personalization in Goal-Oriented Dialog , 2017, ArXiv.

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

[25]  J. A. Troyano,et al.  Managing Speaker Identity and User Profiles in a Spoken Dialogue System , 2009 .

[26]  Ruth Aylett,et al.  An initial memory model for virtual and robot companions supporting migration and long-term interaction , 2009, RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication.

[27]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

[29]  Javier Ferreiros,et al.  Managin speaker identity and user profiles in a spoken dialogue system , 2009 .

[30]  Matthew Henderson,et al.  The third Dialog State Tracking Challenge , 2014, 2014 IEEE Spoken Language Technology Workshop (SLT).

[31]  Xiaofei Lu.  The Relationship of Lexical Richness to the Quality of ESL Learners' Oral Narratives. , 2012 .

[32]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[33]  Tetsuo Ono,et al.  Reading a robot's mind: a model of utterance understanding based on the theory of mind mechanism , 2000, AAAI/IAAI.

[34]  Matthew Henderson,et al.  The Second Dialog State Tracking Challenge , 2014, SIGDIAL Conference.

[35]  Matthew Henderson,et al.  Deep Neural Network Approach for the Dialog State Tracking Challenge , 2013, SIGDIAL Conference.

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

[37]  Dilek Z. Hakkani-Tür,et al.  Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations , 2019, INTERSPEECH.

[38]  Milica Gasic,et al.  POMDP-Based Statistical Spoken Dialog Systems: A Review , 2013, Proceedings of the IEEE.

[39]  Jason Weston,et al.  StarSpace: Embed All The Things! , 2017, AAAI.

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