2021/08/26 by Fengyu Cai, Wanhao Zhou, Cai, Fengyu +5 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Natural Language Processing Techniques #Software Engineering Research #Software System Performance and Reliability
paper · pdf · doi:10.48550/arxiv.2108.11711
openalex publication_date 2021/08/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems. Most existing approaches assume that only a single intent exists in an utterance. However, there are often multiple intents within an utterance in real-life scenarios. In this paper, we propose a multi-intent NLU framework, called SLIM, to jointly learn multi-intent detection and slot filling based on BERT. To fully exploit the existing annotation data and capture the interactions between slots and intents, SLIM introduces an explicit slot-intent classifier to learn the many-to-one mapping between slots and intents. Empirical results on three public multi-intent datasets demonstrate (1) the superior performance of SLIM compared to the current state-of-the-art for NLU with multiple intents and (2) the benefits obtained from the slot-intent classifier.