GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
This work addresses efficiency and accuracy problems for multi-intent spoken language understanding systems, representing an incremental improvement over existing autoregressive methods.
The paper tackled the slow inference speed and information leakage issues in joint multiple intent detection and slot filling by proposing a non-autoregressive model called GL-GIN, which achieved state-of-the-art performance and was 11.5 times faster on two public datasets.
Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing attention. However, the state-of-the-art joint models heavily rely on autoregressive approaches, resulting in two issues: slow inference speed and information leakage. In this paper, we explore a non-autoregressive model for joint multiple intent detection and slot filling, achieving more fast and accurate. Specifically, we propose a Global-Locally Graph Interaction Network (GL-GIN) where a local slot-aware graph interaction layer is proposed to model slot dependency for alleviating uncoordinated slots problem while a global intent-slot graph interaction layer is introduced to model the interaction between multiple intents and all slots in the utterance. Experimental results on two public datasets show that our framework achieves state-of-the-art performance while being 11.5 times faster.