A Hybrid Model Based on Graph Convolutional Network and Multi-head Transformer for Joint Multiple Intent Detection and Slot Filling

Dongsheng Li, Kun Niu, Xiao Chen, Zhihai Wang

Abstract: Recent research has increasingly focused on multiple intent detection and slot filling tasks due to the closer to the complex multi-intent scenarios in the real world. However, existing approaches face two potential issues: (i) Single joint models are unable to capture full information and handle complex relations in data, and (ii) Irrelevant label relations can lead to over-guidance when conducting explicit interactions in multi-intent scenarios. To address the above issues, we propose a hybrid model based on Graph Convolutional Network and Multi-head Transformer (GCN-MT). This model alleviates over-guidance through a graph network at the entire corpus level and realizes intent-slot interaction through a co-attention network at both the specific utterance and local token levels. Experimental results demonstrate that our approach outperforms existing reproducible models on two public multi-intent datasets.