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

Details of Research Outputs

Title	A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding
Creator	Cheng，Lizhi 1; Yang，Wenmian 2; Jia，Weijia 3
Date Issued	2023-06-27
Source Publication	Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Volume	37
Pages	12691-12699
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.
URL	View source
Language	英语English
Scopus ID	2-s2.0-85167973707
Citation statistics
Document Type	Conference paper
Identifier	http://repository.uic.edu.cn/handle/39GCC9TT/11573
Collection	Beijing Normal-Hong Kong Baptist University
Corresponding Author	Yang，Wenmian
Affiliation	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
Recommended Citation 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.

Files in This Item:
There are no files associated with this item.

Related Services

Usage statistics

Google Scholar

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh