SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
This addresses the limitation of existing systems that assume single intents, improving NLU for task-oriented systems in real-life multi-intent scenarios, though it is incremental as it builds on BERT.
The paper tackled the problem of multi-intent detection and slot filling in natural language understanding by proposing SLIM, a framework that introduces an explicit slot-intent classifier based on BERT, achieving superior performance on three public datasets.
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.