Partner Personas Generation for Diverse Dialogue Generation
This work addresses a practical limitation in dialogue systems where partner personas are often missing, offering an incremental improvement over prior methods focused on self personas.
The paper tackles the problem of generating diverse dialogue responses by automatically creating partner personas when ground truth is unavailable, using a reinforcement learning framework with a custom critic network. Experimental results show the framework generates relevant partner personas and enhances response quality, outperforming baselines in both automatic and human evaluations.
Incorporating personas information allows diverse and engaging responses in dialogue response generation. Unfortunately, prior works have primarily focused on self personas and have overlooked the value of partner personas. Moreover, in practical applications, the availability of ground truth partner personas is often not the case. This paper attempts to tackle these issues by offering a novel framework that leverages automatic partner personas generation to enhance the succeeding dialogue generation. We incorporate reinforcement learning with a dedicatedly designed critic network for reward judgement. Experimental results from both automatic and human evaluation demonstrate a) Our framework is capable of generating relevant, informative and coherent partner personas, even compared to the ground truth partner personas. b) Generated partner personas enhance the succeeding response generation, thus surpassing our baselines and comparison model when partner personas are missing during the inference stage. c) Our framework generates responses that are more informative and engaging than our baseline conditioned on the ground truth partner personas during inference. d) Our dedicatedly designed critic network reinforces our framework effectively. Finally, our framework gives better explainability and reduces the demands for external databases for partner personas.