Parameter Differentiation Based Multilingual Neural Machine Translation | |
Wang, Qian; Zhang, Jiajun | |
2022 | |
会议日期 | Feb 22, 2022 |
会议地点 | Virtual Event |
英文摘要 | Multilingual neural machine translation (MNMT) aims to translate multiple languages with a single model and has been proved successful thanks to effective knowledge transfer among different languages with shared parameters. However, it is still an open question which parameters should be shared and which ones need to be task-specific. Currently, the common practice is to heuristically design or search languagespecific modules, which is difficult to find the optimal configuration. In this paper, we propose a novel parameter differentiation based method that allows the model to determine which parameters should be language-specific during training. Inspired by cellular differentiation, each shared parameter in our method can dynamically differentiate into more specialized types. We further define the differentiation criterion as inter-task gradient similarity. Therefore, parameters with conflicting inter-task gradients are more likely to be language-specific. Extensive experiments on multilingual datasets have demonstrated that our method significantly outperforms various strong baselines with different parameter sharing configurations. Further analyses reveal that the parameter sharing configuration obtained by our method correlates well with the linguistic proximities. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/50602] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, Institute of Automation, CAS |
推荐引用方式 GB/T 7714 | Wang, Qian,Zhang, Jiajun. Parameter Differentiation Based Multilingual Neural Machine Translation[C]. 见:. Virtual Event. Feb 22, 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