CASIA OpenIR  > 自然语言处理团队
Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
He Bai; Yu Zhou; Jiajun Zhang; Chengqing Zong
2019
Conference NameACL-2019
Conference Date2019
Conference PlaceFlorence, Italia
Abstract

Dialogue contexts are proven helpful in the spoken language understanding (SLU) system and they are typically encoded with explicit memory representations. However, most of the previous models learn the context memory with only one objective to maximizing the SLU performance, leaving the context memory under-exploited. In this paper, we propose a new dialogue logistic inference (DLI) task to consolidate the context memory jointly with SLU in the multi-task framework. DLI is defined as sorting a shuffled dialogue session into its original logical order and shares the same memory encoder and retrieval mechanism as the SLU model. Our experimental results show that various popular contextual SLU models can benefit from our approach, and improvements are quite impressive, especially in slot filling.

Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/26136
Collection自然语言处理团队
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
He Bai,Yu Zhou,Jiajun Zhang,et al. Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference[C],2019.
Files in This Item: Download All
File Name/Size DocType Version Access License
P19-1541.pdf(380KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He Bai]'s Articles
[Yu Zhou]'s Articles
[Jiajun Zhang]'s Articles
Baidu academic
Similar articles in Baidu academic
[He Bai]'s Articles
[Yu Zhou]'s Articles
[Jiajun Zhang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He Bai]'s Articles
[Yu Zhou]'s Articles
[Jiajun Zhang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: P19-1541.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.