Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition

arXiv:2403.18973v1 Announce Type: new
Abstract: We present Conformal Intent Classification and Clarification (CICC), a framework for fast and accurate intent classification for task-oriented dialogue systems. The framework turns heuristic uncertainty scores of any intent classifier into a clarification question that is guaranteed to contain the true intent at a pre-defined confidence level. By disambiguating between a small number of likely intents, the user query can be resolved quickly and accurately. Additionally, we propose to augment the framework for out-of-scope detection. …

abstract arxiv classification classifier cs.cl dialogue framework question recognition systems true type uncertainty