ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
This addresses the problem of data scarcity in intent detection for NLP applications, though it is incremental as it builds on existing Prototypical Networks.
The paper tackles few-shot intent detection by proposing ProtAugment, a meta-learning algorithm that uses unsupervised diverse paraphrasing to limit overfitting, achieving state-of-the-art results without extra labeling or domain-specific fine-tuning.
Recent research considers few-shot intent detection as a meta-learning problem: the model is learning to learn from a consecutive set of small tasks named episodes. In this work, we propose ProtAugment, a meta-learning algorithm for short texts classification (the intent detection task). ProtAugment is a novel extension of Prototypical Networks, that limits overfitting on the bias introduced by the few-shots classification objective at each episode. It relies on diverse paraphrasing: a conditional language model is first fine-tuned for paraphrasing, and diversity is later introduced at the decoding stage at each meta-learning episode. The diverse paraphrasing is unsupervised as it is applied to unlabelled data, and then fueled to the Prototypical Network training objective as a consistency loss. ProtAugment is the state-of-the-art method for intent detection meta-learning, at no extra labeling efforts and without the need to fine-tune a conditional language model on a given application domain.