Generative Goal-driven User Simulation for Dialog Management

Aciel Eshky, Ben Allison, Mark Steedman

Research output: Chapter in Book/Report/Conference proceedingConference contribution


User simulation is frequently used to train statistical dialog managers for task-oriented domains. At present, goal-driven simulators (those that have a persistent notion of what they wish to achieve in the dialog) require some task-specific engineering, making them impossible to evaluate intrinsically. Instead, they have been evaluated extrinsically by means of the dialog managers they are intended to train, leading to circularity of argument. In this paper, we propose the first fully generative goal-driven simulator that is fully induced from data, without hand-crafting or goal annotation. Our goals are latent, and take the form of topics in a topic model, clustering together semantically equivalent and phonetically confusable strings, implicitly modelling synonymy and speech recognition noise. We evaluate on two standard dialog resources, the Communicator and Let's Go datasets, and demonstrate that our model has substantially better fit to held out data than competing approaches. We also show that features derived from our model allow significantly greater improvement over a baseline at distinguishing real from randomly permuted dialogs.
Original languageEnglish
Title of host publicationProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Number of pages11
Publication statusPublished - 2012


Dive into the research topics of 'Generative Goal-driven User Simulation for Dialog Management'. Together they form a unique fingerprint.

Cite this