[3R1-OS-45] OS-45

[3R1-OS-45-05] Joint Optimization of Post-Processing for All Modules in Task-Oriented Dialogue Systems

〇Atsumoto Ohashi¹, Ryuichiro Higashinaka¹ (1. Nagoya University)

Keywords:Task-oriented dialogue, Language model, Reinforcement learning

Post-Processing Networks (PPNs) serve as components that modify outputs from modules in task-oriented dialogue systems, with the goal of enhancing the system's overall task completion capabilities. Traditional PPN approaches, however, have been restricted to handling only a subset of modules within a system, which has significantly constrained potential performance improvements. In this paper, we introduce a method for simultaneously optimizing the post-processing of the outputs of all modules using Universal Post-Processing Networks (UniPPNs). The UniPPN utilizes a single language model capable of processing outputs from any module as a sequence transformation task. We provide a detailed explanation of the UniPPN reinforcement learning algorithm and demonstrate, through both simulation experiments using the MultiWOZ dataset and human evaluation studies, that our approach achieves superior performance compared to conventional PPN approaches.