Zero-shot intent detection (ZSID) aims to deal with the continuously emerging intents without annotated training data. However, existing ZSID systems suffer from two limitations: 1) They are not good at modeling the relationship between seen and unseen intents. 2) They cannot effectively recognize unseen intents under the generalized intent detection (GZSID) setting. A critical problem behind these limitations is that the representations of unseen intents cannot be learned in the training stage. To address this problem, we propose a novel framework that utilizes unseen class labels to learn Class-Transductive Intent Representations (CTIR). Specifically, we allow the model to predict unseen intents during training, with the corresponding label names serving as input utterances. On this basis, we introduce a multi-task learning objective, which encourages the model to learn the distinctions among intents, and a similarity scorer, which estimates the connections among intents more accurately. CTIR is easy to implement and can be integrated with existing methods. Experiments on two real-world datasets show that CTIR brings considerable improvement to the baseline systems.

翻译：零射意图探测(ZSID)旨在处理不断出现的意图,而没有附加说明的培训数据;然而,现有的ZSID系统存在两个限制:(1) 它们不善于模拟所见意图和不可见意图之间的关系;(2) 它们无法有效认识普遍意图探测(GZSID)所设定的无形意图;这些限制背后的一个关键问题是,在培训阶段无法了解无形意图的表示;为解决这一问题,我们提议了一个新的框架,利用隐蔽的类标签来学习等级转移意图说明(CTIR)。具体地说,我们允许该模型在培训期间预测所见的意图,而相应的标签名称作为输入词。在此基础上,我们引入一个多任务学习目标,鼓励模型了解意图和类似性评分之间的差别,该模型更准确地估计意图之间的联系。CTIR易于执行,并且可以与现有方法融合。两个真实世界数据集的实验表明,CTIR使基线系统有了相当大的改进。