Knowledge Commons of Institute of Automation,CAS
Three Strategies to Improve One-to-Many Multilingual Translation | |
Wang,Yining1,2; Zhang,Jiajun1,2,4; Zhai,Feifei5; Xu,Jingfang5; Zong,Chengqing1,2,3 | |
2018-10 | |
会议名称 | Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing |
会议日期 | October 31 - November 4, 2018 |
会议地点 | Brussels, Belgium |
摘要 | Due to the benefits of model compactness, multilingual translation (including many-to-one, many-to-many and one-to-many) based on a universal encoder-decoder architecture attracts more and more attention. However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models. In this work, we introduce three strategies to improve one-to-many multilingual translation by balancing the shared and unique features. Within the architecture of one decoder for all target languages, we first exploit the use of unique initial states for different target languages. Then, we employ a language-dependent positional embeddings. Finally and especially, we propose to divide the hidden cells of the decoder into shared and language-dependent ones. The extensive experiments demonstrate that our proposed methods can obtain remarkable improvements over the strong baselines. Moreover, our strategies can achieve comparable or even better performance than the individually trained translation models. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39231 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Zhang,Jiajun |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA, Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China 4.Beijing Advanced Innovation Center for Language Resources, Beijing, China 5.Sogou Inc., Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang,Yining,Zhang,Jiajun,Zhai,Feifei,et al. Three Strategies to Improve One-to-Many Multilingual Translation[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Three Strategies to (569KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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