Improving Personality Consistency in Conversation by Persona Extending

Abstract

Endowing chatbots with a consistent personality plays a vital role for agents to deliver human-like interactions. However, existing personalized approaches commonly generate responses in light of static predefined personas depicted with textual description, which may severely restrict the interactivity of human and the chatbot, especially when the agent needs to answer the query excluded in the predefined personas, which is so-called out-of-predefined persona problem (named OOP for simplicity). To alleviate the problem, in this paper we propose a novel retrieval-to-prediction paradigm consisting of two subcomponents, namely, (1) Persona Retrieval Model (PRM), it retrieves a persona from a global collection based on a Natural Language Inference (NLI) model, the inferred persona is consistent with the predefined personas; and (2) Posterior-scored Transformer (PS-Transformer), it adopts a persona posterior distribution that further considers the actual personas used in the ground response, maximally mitigating the gap between training and inferring. Furthermore, we present a dataset called IT-ConvAI2 that first highlights the OOP problem in personalized dialogue. Extensive experiments on both IT-ConvAI2 and ConvAI2 demonstrate that our proposed model yields considerable improvements in both automatic metrics and human evaluations.

arXiv commentAccepted by CIKM 2022

References in corpus (15)

• A Neural Conversational Model
• Enhanced LSTM for Natural Language Inference
• Natural Language Inference over Interaction Space
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• Multi-view Intent Disentangle Graph Networks for Bundle Recommendation
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation
• Personalized Dialogue Generation with Diversified Traits
• Generating Persona Consistent Dialogues by Exploiting Natural Language Inference
• Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• Adapting by Pruning: A Case Study on BERT
• The Second Conversational Intelligence Challenge (ConvAI2)
• Target Guided Emotion Aware Chat Machine
• Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
• DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks