References & Citations
Computer Science > Computation and Language
Title: Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition
(Submitted on 27 Mar 2024)
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. In a comparative evaluation using seven intent recognition datasets we find that CICC generates small clarification questions and is capable of out-of-scope detection. CICC can help practitioners and researchers substantially in improving the user experience of dialogue agents with specific clarification questions.
Submission history
From: Floris Den Hengst [view email][v1] Wed, 27 Mar 2024 19:42:01 GMT (9932kb,D)
Link back to: arXiv, form interface, contact.