Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ohashi, Atsumoto, Higashinaka, Ryuichiro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916594750324736
author Ohashi, Atsumoto
Higashinaka, Ryuichiro
author_facet Ohashi, Atsumoto
Higashinaka, Ryuichiro
contents Post-processing networks (PPNs) are components that modify the outputs of arbitrary modules in task-oriented dialogue systems and are optimized using reinforcement learning (RL) to improve the overall task completion capability of the system. However, previous PPN-based approaches have been limited to handling only a subset of modules within a system, which poses a significant limitation in improving the system performance. In this study, we propose a joint optimization method for post-processing the outputs of all modules using universal post-processing networks (UniPPNs), which are language-model-based networks that can modify the outputs of arbitrary modules in a system as a sequence-transformation task. Moreover, our RL algorithm, which employs a module-level Markov decision process, enables fine-grained value and advantage estimation for each module, thereby stabilizing joint learning for post-processing the outputs of all modules. Through both simulation-based and human evaluation experiments using the MultiWOZ dataset, we demonstrated that UniPPN outperforms conventional PPNs in the task completion capability of task-oriented dialogue systems.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems
Ohashi, Atsumoto
Higashinaka, Ryuichiro
Computation and Language
Artificial Intelligence
Post-processing networks (PPNs) are components that modify the outputs of arbitrary modules in task-oriented dialogue systems and are optimized using reinforcement learning (RL) to improve the overall task completion capability of the system. However, previous PPN-based approaches have been limited to handling only a subset of modules within a system, which poses a significant limitation in improving the system performance. In this study, we propose a joint optimization method for post-processing the outputs of all modules using universal post-processing networks (UniPPNs), which are language-model-based networks that can modify the outputs of arbitrary modules in a system as a sequence-transformation task. Moreover, our RL algorithm, which employs a module-level Markov decision process, enables fine-grained value and advantage estimation for each module, thereby stabilizing joint learning for post-processing the outputs of all modules. Through both simulation-based and human evaluation experiments using the MultiWOZ dataset, we demonstrated that UniPPN outperforms conventional PPNs in the task completion capability of task-oriented dialogue systems.
title Universal Post-Processing Networks for Joint Optimization of Modules in Task-Oriented Dialogue Systems
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.00747