AI 中文总结
本文针对多领域对话状态跟踪问题，提出利用预训练BERT模型的可扩展框架，实现零样本泛化，能快速适应新领域，在基于模式的对话（SGD）数据集上评估，性能相比基线有显著提升。
AI 中文摘要
对话状态跟踪（DST）是任务导向型对话系统的核心组件之一。在对话的每一轮中，DST估计用户信念或对话状态，作为下游模块预测系统动作和生成回复的输入。诸如谷歌助手、Siri和Alexa等越来越流行的对话系统应用需要支持大量服务和API，因此对系统可扩展性的关注度不断提高。特别是对于一些训练数据很少或没有训练数据的领域，非常需要转移其他领域现有知识的能力。本文提出了一种用于多领域对话状态跟踪的新型可扩展框架。该系统利用预训练的BERT模型实现零样本泛化，无需额外训练就能轻松快速适应新领域。在最近发布的基于模式的对话（SGD）数据集上评估了模型性能，与之前的基线相比有显著改进。
英文摘要
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.
Comments7 pages, 4 figures. Presented at the DSTC8 workshop, AAAI-20 (poster session)
