Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering | |
Wang, Qian; Zhang, Jiajun | |
2022 | |
会议日期 | October 12–17, 2022 |
会议地点 | Gyeongju, Republic of Korea |
英文摘要 | 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. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/50600] |
专题 | 模式识别国家重点实验室_自然语言处理 |
通讯作者 | Zhang, Jiajun |
作者单位 | 1.Beijing Academy of Artificial Intelligence, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences , Beijing, China 3.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China |
推荐引用方式 GB/T 7714 | Wang, Qian,Zhang, Jiajun. Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering[C]. 见:. Gyeongju, Republic of Korea. October 12–17, 2022. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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