Adversarial learning of neural user simulators for dialogue policy optimisation

06/01/2023
by   Simon Keizer, et al.
0

Reinforcement learning based dialogue policies are typically trained in interaction with a user simulator. To obtain an effective and robust policy, this simulator should generate user behaviour that is both realistic and varied. Current data-driven simulators are trained to accurately model the user behaviour in a dialogue corpus. We propose an alternative method using adversarial learning, with the aim to simulate realistic user behaviour with more variation. We train and evaluate several simulators on a corpus of restaurant search dialogues, and then use them to train dialogue system policies. In policy cross-evaluation experiments we demonstrate that an adversarially trained simulator produces policies with 8.3 than those trained with a maximum likelihood simulator. Subjective results from a crowd-sourced dialogue system user evaluation confirm the effectiveness of adversarially training user simulators.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset