CASIA OpenIR  > 多模态人工智能系统全国重点实验室  > 自然语言处理
Zero-Shot Deployment for Cross-Lingual Dialogue System
Lu, Xiang1,2; Yang, Zhao1,2; Junnan, Zhu1,2; Yu, Zhou1,2,3; Chengqing, Zong1,2
2021-10
Conference NameProceedings of the 10th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC-2021)
Conference DateOctober 13-17, 2021
Conference PlaceQingdao, China
Abstract

The dialogue system is widely used in many application scenarios, while the construction of the dialogue system always faces the difficulty of zero-resource training data. To alleviate that, we propose a knowledge transfer framework to build a dialogue system based on existing machine translators and training data in data-rich language. Specifically, we first generate various kinds of pseudo data with cyclic translation procedure and different data combinations. Then we propose a noise injection method and a multi-task training method for the pipeline system and end-to-end system, respectively. The noise injection method optimizes each module by incorporating machine translation noises into the pipeline process to handle the error propagation problem, thus improving the whole system's robustness. The multi-task training method combines cross-lingual dialogue, monolingual dialogue, and machine translation into the end-to-end dialogue system's training process, thus reducing the impact of noises in pseudo data. The extensive experiments on a real-world e-commerce dataset demonstrate that our methods can achieve remarkable improvements over strong baselines.

KeywordCross-lingual dialogue system Noise injection Multi-task
Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48930
Collection多模态人工智能系统全国重点实验室_自然语言处理
Corresponding AuthorYu, Zhou
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China
3.Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd., Beijing, China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Lu, Xiang,Yang, Zhao,Junnan, Zhu,et al. Zero-Shot Deployment for Cross-Lingual Dialogue System[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
2021lxiang-nlpcc.pdf(532KB)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
[Lu, Xiang]'s Articles
[Yang, Zhao]'s Articles
[Junnan, Zhu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lu, Xiang]'s Articles
[Yang, Zhao]'s Articles
[Junnan, Zhu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lu, Xiang]'s Articles
[Yang, Zhao]'s Articles
[Junnan, Zhu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2021lxiang-nlpcc.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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