Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Learning Class-Transductive Intent Representations for Zero-shot Intent Detection

Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 3922-3928. https://doi.org/10.24963/ijcai.2021/540

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 ZSID and GZSID methods. Experiments on two real-world datasets show that CTIR brings considerable improvement to the baseline systems.
Keywords:
Natural Language Processing: Natural Language Processing
Natural Language Processing: Text Classification