Improving Personality Consistency in Conversation by Persona Extending
This addresses the issue of personality inconsistency in conversational AI for more human-like interactions, though it is incremental as it builds on existing personalized dialogue methods.
The paper tackles the out-of-predefined persona problem in chatbots by proposing a retrieval-to-prediction paradigm with Persona Retrieval Model and Posterior-scored Transformer, achieving considerable improvements in automatic metrics and human evaluations on IT-ConvAI2 and ConvAI2 datasets.
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.