Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems
This work addresses the need for scalable and cost-effective evaluation methods in task-oriented dialogue systems, though it is incremental as it builds on existing user simulation techniques.
The paper tackles the problem of evaluating task-oriented dialogue systems by proposing a task to simulate user satisfaction, and it introduces a dataset of 6,800 dialogues with satisfaction labels, showing that hierarchical GRU and BERT models achieve the best performance in in-domain and cross-domain prediction, respectively.
Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale automatic evaluation. To help build a human-like user simulator that can measure the quality of a dialogue, we propose the following task: simulating user satisfaction for the evaluation of task-oriented dialogue systems. The purpose of the task is to increase the evaluation power of user simulations and to make the simulation more human-like. To overcome a lack of annotated data, we propose a user satisfaction annotation dataset, USS, that includes 6,800 dialogues sampled from multiple domains, spanning real-world e-commerce dialogues, task-oriented dialogues constructed through Wizard-of-Oz experiments, and movie recommendation dialogues. All user utterances in those dialogues, as well as the dialogues themselves, have been labeled based on a 5-level satisfaction scale. We also share three baseline methods for user satisfaction prediction and action prediction tasks. Experiments conducted on the USS dataset suggest that distributed representations outperform feature-based methods. A model based on hierarchical GRUs achieves the best performance in in-domain user satisfaction prediction, while a BERT-based model has better cross-domain generalization ability.