论文标题
学习零击意图检测的课堂转移意图表示
Learning Class-Transductive Intent Representations for Zero-shot Intent Detection
论文作者
论文摘要
零射击意图检测（ZSID）旨在处理无带注释的培训数据的连续出现的意图。但是，现有的ZSID系统遭受了两个局限性：1）它们不擅长建模可见和看不见的意图之间的关系。 2）他们无法在广义意图检测（GZSID）设置下有效地识别出看不见的意图。这些局限性背后的一个关键问题是，在培训阶段无法学习看不见的意图的表示。为了解决这个问题，我们提出了一个新颖的框架，该框架利用看不见的类标签来学习类转移意图表示（CTIR）。具体而言，我们允许模型在训练过程中预测看不见的意图，相应的标签名称用作输入话语。在此基础上，我们引入了一个多任务学习目标，该目标鼓励模型学习意图之间的区别以及相似性得分手，该目标得出了更准确的估计意图之间的联系。 CTIR易于实现，可以与现有方法集成。两个现实世界数据集的实验表明，CTIR为基线系统带来了可观的改进。
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.
