Persona Authentication through Generative Dialogue

In this paper we define and investigate the problem of persona authentication: learning a conversational policy to verify the consistency of persona models. We propose a learning objective and prove (under some mild assumptions) that local density estimators trained under this objective maximize the mutual information between persona information and dialog trajectory. Based on the proposed objective, we develop a method of learning an authentication model that adaptively outputs personalized questions to reveal the underlying persona of its partner throughout the course of multi-turn conversation. Experiments show that our authentication method discovers effective question sequences that generalize to unseen persona profiles.

[1]  Edward J. Delp,et al.  Deepfake Video Detection Using Recurrent Neural Networks , 2018, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).

[2]  Zhou Yu,et al.  Strategy and Policy Learning for Non-Task-Oriented Conversational Systems , 2016, SIGDIAL Conference.

[3]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[4]  Alec Radford,et al.  Release Strategies and the Social Impacts of Language Models , 2019, ArXiv.

[5]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

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

[7]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[8]  Lav R. Varshney,et al.  CTRL: A Conditional Transformer Language Model for Controllable Generation , 2019, ArXiv.

[9]  Joelle Pineau,et al.  The Second Conversational Intelligence Challenge (ConvAI2) , 2019, The NeurIPS '18 Competition.

[10]  Fu Jie Huang,et al.  A Tutorial on Energy-Based Learning , 2006 .

[11]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[12]  David Silver,et al.  Deep Reinforcement Learning with Double Q-Learning , 2015, AAAI.

[13]  Sham M. Kakade,et al.  On the sample complexity of reinforcement learning. , 2003 .

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

[15]  Yejin Choi,et al.  The Curious Case of Neural Text Degeneration , 2019, ICLR.

[16]  Jianfeng Gao,et al.  DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation , 2020, ACL.

[17]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[18]  Lysandre Debut,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[19]  Miles Brundage,et al.  Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models , 2021, ArXiv.

[20]  Thomas Wolf,et al.  TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents , 2019, ArXiv.

[21]  S. Arikawa,et al.  Byte Pair Encoding: a Text Compression Scheme That Accelerates Pattern Matching , 1999 .