2023/02/22 by Thibault Cordier, Tanguy Urvoy, Cordier, Thibault +5 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Intelligent Tutoring Systems and Adaptive Learning #Speech and dialogue systems #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2302.11199
openalex publication_date 2023/02/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour. The ability to learn from a small number of human interactions is hence crucial, especially on multi-domain and multi-task environments where the action space is large. We therefore propose to use structured policies to improve sample efficiency when learning on these kinds of environments. We also evaluate the impact of learning from human vs simulated experts. Among the different levels of structure that we tested, the graph neural networks (GNNs) show a remarkable superiority by reaching a success rate above 80% with only 50 dialogues, when learning from simulated experts. They also show superiority when learning from human experts, although a performance drop was observed, indicating a possible difficulty in capturing the variability of human strategies. We therefore suggest to concentrate future research efforts on bridging the gap between human data, simulators and automatic evaluators in dialogue frameworks.