Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
This work addresses the challenge of accurate knowledge retrieval in real-life task-oriented dialog systems, which is incremental as it builds on existing retrieval-augmented methods from question answering and document-grounded dialogs.
The paper tackles the problem of noisy user utterances in task-oriented dialog systems by proposing a retrieval-based method for knowledge selection, which significantly outperforms traditional database query methods, and introduces a semi-supervised learning approach that leverages both labeled and unlabeled data to achieve superior performance on a real-life dataset.
Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses. In real-life applications, user utterances are noisier, and thus it is more difficult to accurately track dialog states and correctly secure relevant knowledge. Recently, a progress in question answering and document-grounded dialog systems is retrieval-augmented methods with a knowledge retriever. Inspired by such progress, we propose a retrieval-based method to enhance knowledge selection in TOD systems, which significantly outperforms the traditional database query method for real-life dialogs. Further, we develop latent variable model based semi-supervised learning, which can work with the knowledge retriever to leverage both labeled and unlabeled dialog data. Joint Stochastic Approximation (JSA) algorithm is employed for semi-supervised model training, and the whole system is referred to as that JSA-KRTOD. Experiments are conducted on a real-life dataset from China Mobile Custom-Service, called MobileCS, and show that JSA-KRTOD achieves superior performances in both labeled-only and semi-supervised settings.