A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding
This addresses error propagation in multi-intent SLU, a domain-specific incremental improvement for speech and language processing.
The paper tackles the problem of multi-intent spoken language understanding, where each intent has a specific scope and out-of-scope information hinders prediction, by proposing a Scope-Sensitive Result Attention Network (SSRAN) that improves overall accuracy by 5.4% and 2.1% on two datasets compared to state-of-the-art baselines.
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.