CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering
Wang, Qian; Zhang, Jiajun
Conference Name29th International Conference on Computational Linguistics
Conference DateOctober 12–17, 2022
Conference PlaceGyeongju, Republic of Korea

Multilingual neural machine translation (NMT) enables positive knowledge transfer among multiple translation tasks with a shared underlying model, but a unified multilingual model usually suffers from capacity bottleneck when tens or hundreds of languages are involved. A possible solution is to cluster languages and train individual model for each cluster. However, the existing clustering methods based on language similarity cannot handle the asymmetric problem in multilingual NMT, i.e., one translation task A can benefit from another translation task B but task B will be harmed by task A. To address this problem, we propose a fuzzy task clustering method for multilingual NMT. Specifically, we employ task affinity, defined as the loss change of one translation task caused by the training of another, as the clustering criterion. Next, we cluster the translation tasks based on the task affinity, such that tasks from the same cluster can benefit each other. For each cluster, we further find out a set of auxiliary translation tasks that benefit the tasks in this cluster. In this way, the model for each cluster is trained not only on the tasks in the cluster but also on the auxiliary tasks. During training, we design a dynamic task sampling strategy that eliminate the negative influence of auxiliary tasks while exploit the positive knowledge of them. We conduct extensive experiments for one-to-many, many-to-one, and many-to-many translation scenarios to verify the effectiveness of our method.

IS Representative Paper
Sub direction classification自然语言处理
planning direction of the national heavy laboratory语音语言处理
Document Type会议论文
Corresponding AuthorZhang, Jiajun
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.Beijing Academy of Artificial Intelligence, Beijing, China
Recommended Citation
GB/T 7714
Wang, Qian,Zhang, Jiajun. Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering[C],2022.
Files in This Item: Download All
File Name/Size DocType Version Access License
2022.coling-1.455.pd(664KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Qian]'s Articles
[Zhang, Jiajun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Qian]'s Articles
[Zhang, Jiajun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Qian]'s Articles
[Zhang, Jiajun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 2022.coling-1.455.pdf
Format: Adobe PDF
All comments (0)
No comment.

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