HAN: Higher-order Attention Network for Spoken Language Understanding

TL;DR

This paper introduces the Higher-order Attention Network (HAN) for Spoken Language Understanding, utilizing bilinear attention to enhance fine-grained feature interaction between intent detection and slot filling tasks.

Contribution

It proposes a novel higher-order attention mechanism with bilinear attention blocks, improving SLU performance by exploring attention order effects.

Findings

HAN outperforms previous attention-based models.

Higher-order attention enhances feature interaction.

Wide analysis confirms effectiveness of attention order exploration.

Abstract

Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction. The natural attributes of the relationship among the two subtasks make higher requirements on fine-grained feature interaction, i.e., the token-level intent features and slot features. Previous works mainly focus on jointly modeling the relationship between the two subtasks with attention-based models, while ignoring the exploration of attention order. In this paper, we propose to replace the conventional attention with our proposed Bilinear attention block and show that the introduced Higher-order Attention Network (HAN) brings improvement for the SLU task. Importantly, we conduct wide analysis to explore the effectiveness brought from the higher-order attention.