科研成果详情

题名An Effective Non-Autoregressive Model for Spoken Language Understanding
作者
发表日期2021-10-26
会议名称30th ACM International Conference on Information and Knowledge Management, CIKM 2021
会议录名称International Conference on Information and Knowledge Management, Proceedings
ISBN978-145038446-9
页码241-250
会议日期NOV 01-05, 2021
会议地点Electronic Network
摘要

Spoken Language Understanding (SLU), a core component of the task-oriented dialogue system, expects a shorter inference latency due to the impatience of humans. Non-autoregressive SLU models clearly increase the inference speed but suffer uncoordinated-slot problems caused by the lack of sequential dependency information among each slot chunk. To gap this shortcoming, in this paper, we propose a novel non-autoregressive SLU model named Layered-Refine Transformer, which contains a Slot Label Generation (SLG) task and a Layered Refine Mechanism (LRM). SLG is defined as generating the next slot label with the token sequence and generated slot labels. With SLG, the non-autoregressive model can efficiently obtain dependency information during training and spend no extra time in inference. LRM predicts the preliminary SLU results from Transformer's middle states and utilizes them to guide the final prediction. Experiments on two public datasets indicate that our model significantly improves SLU performance (1.5% on Overall accuracy) while substantially speed up (more than 10 times) the inference process over the state-of-the-art baseline.

关键词multi-task learning spoken interfaces task-oriented dialogue system
DOI10.1145/3459637.3482229
URL查看来源
收录类别CPCI-S
语种英语English
WOS研究方向Computer Science
WOS类目Computer Science ; Information Systems
WOS记录号WOS:001054156200027
Scopus入藏号2-s2.0-85119208867
引用统计
被引频次:11[WOS]   [WOS记录]     [WOS相关记录]
文献类型会议论文
条目标识符https://repository.uic.edu.cn/handle/39GCC9TT/8311
专题理工科技学院
通讯作者Yang, Wenmian
作者单位
1.Shanghai JiaojinTong University, Shanghai, China
2.Beijing Normal University (BNU Zhuhai), BNU-HKBU United International College, Zhuhai, China
推荐引用方式
GB/T 7714
Cheng, Lizhi,Jia, Weijia,Yang, Wenmian. An Effective Non-Autoregressive Model for Spoken Language Understanding[C], 2021: 241-250.
条目包含的文件
条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Cheng, Lizhi]的文章
[Jia, Weijia]的文章
[Yang, Wenmian]的文章
百度学术
百度学术中相似的文章
[Cheng, Lizhi]的文章
[Jia, Weijia]的文章
[Yang, Wenmian]的文章
必应学术
必应学术中相似的文章
[Cheng, Lizhi]的文章
[Jia, Weijia]的文章
[Yang, Wenmian]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。