Candidate Attended Dialogue State Tracking Using BERT
Computation and LanguageArtificial Intelligence
Summary
The authors focus on dialogue state tracking, which helps virtual assistants understand what users want during a conversation. They built a system that can handle many different topics by using a pretrained model called BERT, allowing it to work well even on new topics without extra training. Their approach was tested on a recent dataset and performed better than older methods. This makes it easier to add new services to dialogue systems quickly.
Authors
Junyuan Zheng, Onkar Salvi, John Chan
Abstract
Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream modules to predict system actions and generate responses. The increasingly popular dialogue system applications like Google Assistant, Siri and Alexa need to support a large number of services and APIs, resulting in growing attention to the scalability of such systems. Especially for some domains with little or no training data, the capability of transferring existing knowledge of other domains is highly desired. In this paper, we present a novel scalable framework for multi-domain dialogue state tracking. The proposed system leverages the pretrained BERT model to achieve zero-shot generalization, making it easy to quickly adapt to new domains without additional training. The performance of our model is evaluated on recently released schema-based dialogue (SGD) dataset, showing significant improvement compared to previous baseline.