A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification
This work addresses the challenge of scalable data collection for conversational AI agents like Amazon Alexa and Apple Siri, though it is incremental as it builds on existing data augmentation and representation learning methods.
The paper tackles the problem of poor generalization in conversational AI when only a few examples are available for new intents, by studying feature space data augmentation methods in a few-shot setting, showing that these methods improve intent classification performance beyond traditional transfer learning approaches, with specific techniques like upsampling in latent space and adding differences between examples proving effective.
New conversation topics and functionalities are constantly being added to conversational AI agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable and is often costly, only a handful of examples for the new functionalities are available, which results in poor generalization performance. We formulate it as a Few-Shot Integration (FSI) problem where a few examples are used to introduce a new intent. In this paper, we study six feature space data augmentation methods to improve classification performance in FSI setting in combination with both supervised and unsupervised representation learning methods such as BERT. Through realistic experiments on two public conversational datasets, SNIPS, and the Facebook Dialog corpus, we show that data augmentation in feature space provides an effective way to improve intent classification performance in few-shot setting beyond traditional transfer learning approaches. In particular, we show that (a) upsampling in latent space is a competitive baseline for feature space augmentation (b) adding the difference between two examples to a new example is a simple yet effective data augmentation method.