All Labels Together: Low-shot Intent Detection with an Efficient Label Semantic Encoding Paradigm
This addresses the challenge of intent detection with limited training data, which is incremental as it builds on existing methods by better leveraging label information.
The paper tackles the problem of few-shot intent detection by proposing an end-to-end system that fully utilizes label semantics, achieving state-of-the-art performance in 1-, 3-, and 5-shot settings and enabling zero-shot cross-domain generalization.
In intent detection tasks, leveraging meaningful semantic information from intent labels can be particularly beneficial for few-shot scenarios. However, existing few-shot intent detection methods either ignore the intent labels, (e.g. treating intents as indices) or do not fully utilize this information (e.g. only using part of the intent labels). In this work, we present an end-to-end One-to-All system that enables the comparison of an input utterance with all label candidates. The system can then fully utilize label semantics in this way. Experiments on three few-shot intent detection tasks demonstrate that One-to-All is especially effective when the training resource is extremely scarce, achieving state-of-the-art performance in 1-, 3- and 5-shot settings. Moreover, we present a novel pretraining strategy for our model that utilizes indirect supervision from paraphrasing, enabling zero-shot cross-domain generalization on intent detection tasks. Our code is at https://github.com/jiangshdd/AllLablesTogether.