natural language understanding (NLU) is a vital component of dialogue
systems, and its ability to detect Out-of-Domain (OOD) inputs is critical in
practical applications, since the acceptance of the OOD input that is
unsupported by the current system may lead to catastrophic failure. H
本文介绍了通过使用变分自编码器、非监督聚类等方法,解决了任务导向型对话系统中存在的 Out of Scope,Out of Domain 等输入识别问题,以及训练 Intent Detection 模型时的数据集标注问题。在英文和波斯语中的实验结果表明,我们的模型在同时实现 OOD/OOS 意图检测和意图发现方面取得了优异的性能效果,超越了基准线。