QAID: Question Answering Inspired Few-shot Intent Detection

Intent detection with semantically similar fine-grained intents is a challenging task. To address it, we reformulate intent detection as a question-answering task by treating utterances and intent names as questions and answers. To that end, we utilize a question-answering retrieval architecture and adopt a two stages training schema with batch contrastive loss. In the first stage, we train the model to learn better query representation in a self supervise manner. Then, in the second stage, we fine-tune the model to optimize contextualized token-level similarity scores between queries and answers from the same intent. Our results on three few-shot intent detection benchmarks achieve state-of-the-art performance.