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
![]() |
ISBN | 978-145038446-9 |
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 |
DOI | 10.1145/3459637.3482229 |
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 | |
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。 |
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。
修改评论