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

科研成果详情

题名	A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding
作者	Cheng，Lizhi 1; Yang，Wenmian 2; Jia，Weijia 3
发表日期	2023-06-27
会议录名称	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
卷号	37
页码	12691-12699
摘要	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.
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85167973707
引用统计
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/11573
专题	北师香港浸会大学
通讯作者	Yang，Wenmian
作者单位	1.Shanghai Jiao Tong University,Shanghai,China 2.Nanyang Technological University,Singapore,Singapore 3.BNU-UIC Institute of Artificial Intelligence and Future Networks,Beijing Normal University (Zhuhai),Guangdong Key Lab of AI and Multi-Modal Data Processing,BNU-HKBU United International College,Zhuhai,Guang Dong,China
推荐引用方式 GB/T 7714	Cheng，Lizhi,Yang，Wenmian,Jia，Weijia. A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding[C], 2023: 12691-12699.