A Co-Interactive Transformer for Joint Slot Filling and Intent Detection
This work addresses the need for more accurate spoken language understanding systems by modeling bidirectional interactions between slot filling and intent detection, representing an incremental advance over prior methods that only considered unidirectional flows.
The paper tackled the problem of joint slot filling and intent detection in spoken language understanding by proposing a Co-Interactive Transformer that models bidirectional connections between the tasks, achieving state-of-the-art performance with improvements of +3.4% and +0.9% in overall accuracy on SNIPS and ATIS datasets.
Intent detection and slot filling are two main tasks for building a spoken language understanding (SLU) system. The two tasks are closely related and the information of one task can be utilized in the other task. Previous studies either model the two tasks separately or only consider the single information flow from intent to slot. None of the prior approaches model the bidirectional connection between the two tasks simultaneously. In this paper, we propose a Co-Interactive Transformer to consider the cross-impact between the two tasks. Instead of adopting the self-attention mechanism in vanilla Transformer, we propose a co-interactive module to consider the cross-impact by building a bidirectional connection between the two related tasks. In addition, the proposed co-interactive module can be stacked to incrementally enhance each other with mutual features. The experimental results on two public datasets (SNIPS and ATIS) show that our model achieves the state-of-the-art performance with considerable improvements (+3.4% and +0.9% on overall acc). Extensive experiments empirically verify that our model successfully captures the mutual interaction knowledge.