Generating Persona Consistent Dialogues by Exploiting Natural Language Inference

Abstract

Consistency is one of the major challenges faced by dialogue agents. A human-like dialogue agent should not only respond naturally, but also maintain a consistent persona. In this paper, we exploit the advantages of natural language inference (NLI) technique to address the issue of generating persona consistent dialogues. Different from existing work that re-ranks the retrieved responses through an NLI model, we cast the task as a reinforcement learning problem and propose to exploit the NLI signals from response-persona pairs as rewards for the process of dialogue generation. Specifically, our generator employs an attention-based encoder-decoder to generate persona-based responses. Our evaluator consists of two components: an adversarially trained naturalness module and an NLI based consistency module. Moreover, we use another well-performed NLI model in the evaluation of persona-consistency. Experimental results on both human and automatic metrics, including the model-based consistency evaluation, demonstrate that the proposed approach outperforms strong generative baselines, especially in the persona-consistency of generated responses.

arXiv commentAAAI20. Update code links

References in corpus (18)

• Sequence to Sequence Learning with Neural Networks
• A Neural Conversational Model
• Enhanced LSTM for Natural Language Inference
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• A large annotated corpus for learning natural language inference
• Deep Reinforcement Learning for Dialogue Generation
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Natural Language Inference over Interaction Space
• Adversarial Learning for Neural Dialogue Generation
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• A Persona-Based Neural Conversation Model
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
• Exploiting Persona Information for Diverse Generation of Conversational Responses
• A Study of Reinforcement Learning for Neural Machine Translation
• Deep Reinforcement Learning for Chinese Zero pronoun Resolution
• Retrieval-Enhanced Adversarial Training for Neural Response Generation

Cited by in corpus (12)

• Survey of Hallucination in Natural Language Generation
• One Chatbot Per Person: Creating Personalized Chatbots based on Implicit User Profiles
• Learning Implicit User Profiles for Personalized Retrieval-Based Chatbot
• Improving Personality Consistency in Conversation by Persona Extending
• You Impress Me: Dialogue Generation via Mutual Persona Perception
• Profile Consistency Identification for Open-domain Dialogue Agents
• COSPLAY: Concept Set Guided Personalized Dialogue Generation Across Both Party Personas
• Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation
• Generating Personalized Dialogue via Multi-Task Meta-Learning
• Will I Sound Like Me? Improving Persona Consistency in Dialogues through Pragmatic Self-Consciousness
• From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation
• Identifying Untrustworthy Samples: Data Filtering for Open-domain Dialogues with Bayesian Optimization