A Fast Attention Network for Joint Intent Detection and Slot Filling on Edge Devices
This work addresses the need for efficient natural language understanding in task-oriented dialogue systems deployed on resource-constrained edge devices, representing an incremental improvement.
The paper tackles the problem of high inference latency in joint intent detection and slot filling models for edge devices by proposing a Fast Attention Network (FAN), which improves semantic accuracy by over 2% and achieves 15 inferences per second on a Jetson Nano platform.
Intent detection and slot filling are two main tasks in natural language understanding and play an essential role in task-oriented dialogue systems. The joint learning of both tasks can improve inference accuracy and is popular in recent works. However, most joint models ignore the inference latency and cannot meet the need to deploy dialogue systems at the edge. In this paper, we propose a Fast Attention Network (FAN) for joint intent detection and slot filling tasks, guaranteeing both accuracy and latency. Specifically, we introduce a clean and parameter-refined attention module to enhance the information exchange between intent and slot, improving semantic accuracy by more than 2%. FAN can be implemented on different encoders and delivers more accurate models at every speed level. Our experiments on the Jetson Nano platform show that FAN inferences fifteen utterances per second with a small accuracy drop, showing its effectiveness and efficiency on edge devices.