A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding

TL;DR

This paper introduces SSRAN, a Transformer-based model for multi-intent SLU that uses scope recognition and result attention to improve intent detection and slot filling accuracy, addressing scope and error propagation challenges.

Contribution

The paper proposes a novel SSRAN model with scope recognition and result attention mechanisms to enhance multi-intent SLU performance.

Findings

Achieved 5.4% and 2.1% improvements in overall accuracy on two datasets.

Effectively reduces distraction from out-of-scope tokens.

Mitigates error propagation between intent detection and slot filling.

Abstract

Multi-Intent Spoken Language Understanding (SLU), a novel and more complex scenario of SLU, is attracting increasing attention. Unlike traditional SLU, each intent in this scenario has its specific scope. Semantic information outside the scope even hinders the prediction, which tremendously increases the difficulty of intent detection. More seriously, guiding slot filling with these inaccurate intent labels suffers error propagation problems, resulting in unsatisfied overall performance. To solve these challenges, in this paper, we propose a novel Scope-Sensitive Result Attention Network (SSRAN) based on Transformer, which contains a Scope Recognizer (SR) and a Result Attention Network (RAN). Scope Recognizer assignments scope information to each token, reducing the distraction of out-of-scope tokens. Result Attention Network effectively utilizes the bidirectional interaction between results of slot filling and intent detection, mitigating the error propagation problem. Experiments on two public datasets indicate that our model significantly improves SLU performance (5.4\% and 2.1\% on Overall accuracy) over the state-of-the-art baseline.