Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc. With the increasing need to deploy such systems in new domains, solving the problem of zero/few-shot DST has become necessary. There has been a rising trend for learning to transfer knowledge from resource-rich domains to unknown domains with minimal need for additional data. In this work, we explore the merits of meta-learning algorithms for this transfer and hence, propose a meta-learner D-REPTILE specific to the DST problem. With extensive experimentation, we provide clear evidence of benefits over conventional approaches across different domains, methods, base models, and datasets with significant (5-25%) improvement over the baseline in a low-data setting. Our proposed meta-learner is agnostic of the underlying model and hence any existing state-of-the-art DST system can improve its performance on unknown domains using our training strategy.
翻译:国家对话跟踪(DST)构成自动聊天室系统的核心组成部分,这些系统是为旅馆、出租车预订、旅游信息等具体目标设计的。随着越来越需要在新领域部署这种系统,解决零/低发DST问题变得十分必要。学习将知识从资源丰富的领域转移到最不需要额外数据的未知领域的趋势不断上升。在这项工作中,我们探索了这种转让的元学习算法的优点,因此,提出了针对DST问题的元learner D-REPTILE。通过广泛的实验,我们提供了明确的证据,表明在不同领域、方法、基建模型和数据集的常规方法上的好处,在低数据环境下,比基线(5-25%)有显著改进。我们提议的元learner对基本模型是敏感的,因此,任何现有的最先进的DST系统都可以利用我们的培训战略,在未知领域改进其绩效。