Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks
This work provides an incremental improvement in spoken language understanding performance for developers building SLU systems.
This paper addresses the problem of joint intent detection and slot filling in spoken language understanding by proposing a Wheel-Graph Attention Network (Wheel-GAT). The model constructs a graph with intent and slot nodes to capture interrelations, and experiments show it outperforms multiple baselines on two public datasets, with further improvements when integrated with BERT.
Intent detection and slot filling are two fundamental tasks for building a spoken language understanding (SLU) system. Multiple deep learning-based joint models have demonstrated excellent results on the two tasks. In this paper, we propose a new joint model with a wheel-graph attention network (Wheel-GAT) which is able to model interrelated connections directly for intent detection and slot filling. To construct a graph structure for utterances, we create intent nodes, slot nodes, and directed edges. Intent nodes can provide utterance-level semantic information for slot filling, while slot nodes can also provide local keyword information for intent. Experiments show that our model outperforms multiple baselines on two public datasets. Besides, we also demonstrate that using Bidirectional Encoder Representation from Transformer (BERT) model further boosts the performance in the SLU task.